SlideShare une entreprise Scribd logo
1  sur  19
Télécharger pour lire hors ligne
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
Universal Bayesian Measures
Joe Suzuki
Osaka University
IEEE International Symposium on Information Theory
Istanbul, Turky
July 8, 2013
1 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
Given n examples, identify whether X, Y are
independent or not
(x1, y1), · · · , (xn, yn) ∼ (X, Y ) ∈ {0, 1} × {0, 1}
p: a prior probability that X, Y are independent
The Bayesian answer
Consider weight W over θ to compute
Qn
(xn
) :=
∫
P(xn
|θ)dW (θ) , Qn
(yn
) :=
∫
P(yn
|θ)dW (θ)
Qn
(xn
, yn
) :=
∫
P(xn
, yn
|θ)dW (θ)
pQn(xn)Qn(yn) ≥ (1 − p)Qn(xn, yn) ⇐⇒ X, Y are independent
2 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
Problem: what if X, Y are arbitrary random variables?
(Ω, F, P): probability space
B: the Borel set of R
 
X is a random variable
.
.
X : Ω → R is F-measurable
(D ∈ B =⇒ {ω ∈ Ω|X(ω) ∈ D} ∈ F)
 
X, Y may be either
discrete
contunuous
none of them
3 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
What Qn
is qualified to be an alternative to Pn
?
True θ = θ∗ is not available
.
.
Pn(xn) = P(xn|θ∗), Pn(yn) = P(yn|θ∗)
Pn(xn, yn) = Pn(xn, yn|θ∗)
Qn
(xn
) :=
∫
P(xn
|θ)dW (θ) , Qn
(yn
) :=
∫
P(yn
|θ)dW (θ)
Qn
(xn
, yn
) :=
∫
P(xn
, yn
|θ)dW (θ)
4 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
Example: Bayes Codes
c: the # of ones in xn
θ: the prob. of ones
P(xn
|θ) = θc
(1 − θ)n−c
a, b > 0
w(θ) ∝
1
θa(1 − θ)b
 
For each xn = (x1, · · · , xn) ∈ {0, 1}n,
Qn
(xn
) :=
∫
w(θ)P(xn
|θ)dθ =
∏c−1
j=0 (j + a) ·
∏n−c−1
k=0 (k + b)
∏n−1
i=0 (i + a + b)
5 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
Universal Coding/Measures
If we choose
a = b = 1/2
(Krichevsky-Trofimov) and xn is i.i.d. emitted by
Pn
(xn
|θ) =
n∏
i=1
P(xi ) , P(xi ) = θ, 1 − θ
then, for any P, almost surely,
−
1
n
log Qn
(xn
) → H :=
∑
x∈A
−P(x) log P(x)
From Shannon McMillian Breiman, for any P,
−
1
n
log Pn
(xn
|θ) =
1
n
n∑
i=1
− log P(xi ) → E[− log P(xi )] = H
6 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
Why Pn
can be replaced by Qn
if n is large ?
For any P, almost surely,
1
n
log
Pn(xn)
Qn(xn)
→ 0 (1)
Qn: a universal Bayesian measure for A
.
What are Qn and (1) in the general settings ?
7 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
Suppose a density function exists for X
A: the range of X
A0 := {A}
Aj+1 is a refinement of Aj
Example 1: if A = [0, 1), the sequence can be A0 = {[0, 1)},
A1 = {[0, 1/2), [1/2, 1)}
A2 = {[0, 1/4), [1/4, 1/2), [1/2, 3/4), [3/4, 1)}
. . .
Aj = {[0, 2−(j−1)), [2−(j−1), 2 · 2−(j−1)), · · · , [(2j−1 − 1)2−(j−1), 1)}
. . .
sj : A → Aj (quantization, x ∈ a ∈ Aj =⇒ sj (x) = a)
λ : R → B (Lebesgue measure, a = [b, c) =⇒ λ(a) = c − b)
Qn
j : a universal Bayesian measure for Aj
8 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
If (sj (x1), · · · , sj (xn)) = (a1, · · · , an),
gn
j (xn
) :=
Qn
j (a1, · · · , an)
λ(a1) · · · λ(an)
f n
j (xn
) := fj (x1) · · · fj (xn) =
Pj (a1) · · · Pj (an)
λ(a1) . . . λ(an)
For {ωj }∞
j=1:
∑
ωj = 1, ωj > 0, gn
(xn
) :=
∞∑
j=1
ωj gn
j (xn
)
For any f and {Aj } s.t. h(fj ) → h(f ) as j → ∞, almost surely
1
n
log
f n(xn)
gn(xn)
→ 0 (2)
B. Ryabko. IEEE Trans. on Inform. Theory, 55, 9, 2009.
9 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
Our Goal: what are they generalized into?
. 1 if the random variable takes finite values:
1
n
log
Pn
(xn
)
Qn(xn)
→ 0 (1)
for any Pn
.
2 if a density function exists:
1
n
log
f n
(xn
)
gn(xn)
→ 0 (2)
for any f n
and {Aj } satisfies h(fj ) → h(f ) as j → ∞
10 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
Exactly when does density function exist?
B: the Borel sets of R
µ(D): the prob. of D ∈ B
When a density function exists
.
The following are equivalent (µ ≪ λ):
for each D ∈ B, λ(D) = 0 =⇒ µ(D) = 0
∃ B-measurable
dµ
dλ
:= f s.t. µ(D) =
∫
D
f (t)dλ(t)
f is the density function (w.r.t. λ).
11 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
Density Functions in a General Sense
Radon-Nikodum’s Theorem
.
.
The following are equivalent (µ ≪ η):
for each D ∈ B, η(D) = 0 =⇒ µ(D) = 0
∃ B-measurable
dµ
dη
:= fη s.t. µ(D) =
∫
D
fη(t)dη(t)
fη is the density function w.r.t. η.
 
Example 2: µ({h}) > 0, η({h}) :=
1
h(h + 1)
, h ∈ B := {1, 2, · · · }
µ ≪ η
µ(D) =
∑
h∈D∩B
fη(h)η({h})
dµ
dη
(h) = fη(h) =
µ({h})
η({h})
= h(h + 1)µ({h})
12 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
B1 := {{1}, {2, 3, · · · }}
B2 := {{1}, {2}, {3, 4, · · · }}
. . .
Bk := {{1}, {2}, · · · , {k}, {k + 1, k + 2, · · · }}
. . .
tk : B → Bk (quantization, y ∈ b ∈ Bk =⇒ tk(y) = b)
If (tk(y1), · · · , tk(yn)) = (b1, · · · , bn),
gn
η,k(yn
) :=
Qn
k (b1, · · · , bn)
η(b1) · · · η(bn)
, gn
η (yn
) :=
∞∑
k=1
ωkgn
η,k(yn
)
For any fη and {Bk} s.t. h(fη,k) → h(fη) , almost surely
1
n
log
f n
η (yn)
gn
η (yn)
→ 0 (3)
gn(yn)
∏n
i=1 ηn({yi }) estimates P(yn) = f n
η (yn)
∏n
i=1 ηn({yi })
13 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
In the general case
µn
(Dn
) :=
∫
D
f n
η (yn
)dηn
(yn
)
νn
(Dn
) :=
∫
D
gn
η (yn
)dηn
(yn
)
f n
η (yn)
gn
η (yn)
=
dµn
dηn
(yn
)/
dνn
dηn
(yn
) =
dµn
dνn
(yn
)
D(µ||ν) :=
∫
dµ log
dµ
dν
h(fη) :=
∫
−f n
η (yn
) log f n
η (yn
)dη(yn
)
= −
∫
dµ
dη
(yn
) log
dµ
dη
(yn
) · dη(yn
) = −D(µ||η)
14 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
Main Theorem
Theorem
.
With probability one as n → ∞
1
n
log
dµn
dνn
(yn
) → 0
for any stationary ergodic µn and {Bk} such that
D(µk||η) → D(µ||η) as k → ∞
15 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
Joint Density Functions
Example 3: A × B (based on Examples 1,2)
µ ≪ λη
A0 × B0 = {A} × {B} = {[0, 1)} × {{1, 2, · · · }}
A1 × B1
A2 × B2
. . .
Aj × Bk
. . .
(sj , tk) : A × B → Aj × Bk
 
If {Aj × Bk} satisfies fλη,jk → fλη, for any fλη, almost surely, we
can construct gn
λη s.t.
1
n
log
f n
λη(xn, yn)
gn
λη(xn, yn)
→ 0 (4)
16 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
The Answer to the Problem
Estimate f n
X (xn), f n
Y (yn), f n
XY (xn, yn) by
gn
X (xn), gn
Y (yn), gn
XY (xn, yn)
 
The Bayesian answer
.
.
pgn
X (xn)gn
Y (yn) ≤ (1 − p)gXY (xn, yn) ⇐⇒ X, Y are independent
17 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
The General Bayesian Solution
Givem n examples zn and prior {pm} over models m = 1, 2, · · · ,
compute gn
(zn
|m) for each m = 1, 2, · · ·
find the model m maxmizing pmg(zn
|m)
18 / 19
Universal Bayesian Measures
Problem Density Functions Generalized Density Functions The Bayesian Solution Summary
Summary and Discussion
Bayesian Measure
.
.
Generalization without assuming Discrete or Continuous
Universality of Bayes/MDL in the generalized sense
Many Applications
Bayesian network structure estimation (DCC 2012)
The Bayesian Chow-Liu Algorithm (PGM 2012)
Markov order estimation even when {Xi } is continuous
19 / 19
Universal Bayesian Measures

Contenu connexe

Tendances

Bayes Independence Test
Bayes Independence TestBayes Independence Test
Bayes Independence TestJoe Suzuki
 
Bellman functions and Lp estimates for paraproducts
Bellman functions and Lp estimates for paraproductsBellman functions and Lp estimates for paraproducts
Bellman functions and Lp estimates for paraproductsVjekoslavKovac1
 
Multilinear Twisted Paraproducts
Multilinear Twisted ParaproductsMultilinear Twisted Paraproducts
Multilinear Twisted ParaproductsVjekoslavKovac1
 
Multilinear singular integrals with entangled structure
Multilinear singular integrals with entangled structureMultilinear singular integrals with entangled structure
Multilinear singular integrals with entangled structureVjekoslavKovac1
 
Scattering theory analogues of several classical estimates in Fourier analysis
Scattering theory analogues of several classical estimates in Fourier analysisScattering theory analogues of several classical estimates in Fourier analysis
Scattering theory analogues of several classical estimates in Fourier analysisVjekoslavKovac1
 
A Generalization of the Chow-Liu Algorithm and its Applications to Artificial...
A Generalization of the Chow-Liu Algorithm and its Applications to Artificial...A Generalization of the Chow-Liu Algorithm and its Applications to Artificial...
A Generalization of the Chow-Liu Algorithm and its Applications to Artificial...Joe Suzuki
 
Bayesian regression models and treed Gaussian process models
Bayesian regression models and treed Gaussian process modelsBayesian regression models and treed Gaussian process models
Bayesian regression models and treed Gaussian process modelsTommaso Rigon
 
A Generalization of Nonparametric Estimation and On-Line Prediction for Stati...
A Generalization of Nonparametric Estimation and On-Line Prediction for Stati...A Generalization of Nonparametric Estimation and On-Line Prediction for Stati...
A Generalization of Nonparametric Estimation and On-Line Prediction for Stati...Joe Suzuki
 
A Conjecture on Strongly Consistent Learning
A Conjecture on Strongly Consistent LearningA Conjecture on Strongly Consistent Learning
A Conjecture on Strongly Consistent LearningJoe Suzuki
 
A sharp nonlinear Hausdorff-Young inequality for small potentials
A sharp nonlinear Hausdorff-Young inequality for small potentialsA sharp nonlinear Hausdorff-Young inequality for small potentials
A sharp nonlinear Hausdorff-Young inequality for small potentialsVjekoslavKovac1
 
S.Duplij, A q-deformed generalization of the Hosszu-Gluskin theorem
S.Duplij, A q-deformed generalization of the Hosszu-Gluskin theoremS.Duplij, A q-deformed generalization of the Hosszu-Gluskin theorem
S.Duplij, A q-deformed generalization of the Hosszu-Gluskin theoremSteven Duplij (Stepan Douplii)
 
Tales on two commuting transformations or flows
Tales on two commuting transformations or flowsTales on two commuting transformations or flows
Tales on two commuting transformations or flowsVjekoslavKovac1
 
Paraproducts with general dilations
Paraproducts with general dilationsParaproducts with general dilations
Paraproducts with general dilationsVjekoslavKovac1
 
A T(1)-type theorem for entangled multilinear Calderon-Zygmund operators
A T(1)-type theorem for entangled multilinear Calderon-Zygmund operatorsA T(1)-type theorem for entangled multilinear Calderon-Zygmund operators
A T(1)-type theorem for entangled multilinear Calderon-Zygmund operatorsVjekoslavKovac1
 
A Szemeredi-type theorem for subsets of the unit cube
A Szemeredi-type theorem for subsets of the unit cubeA Szemeredi-type theorem for subsets of the unit cube
A Szemeredi-type theorem for subsets of the unit cubeVjekoslavKovac1
 
(DL hacks輪読) Deep Kernel Learning
(DL hacks輪読) Deep Kernel Learning(DL hacks輪読) Deep Kernel Learning
(DL hacks輪読) Deep Kernel LearningMasahiro Suzuki
 
A Szemerédi-type theorem for subsets of the unit cube
A Szemerédi-type theorem for subsets of the unit cubeA Szemerédi-type theorem for subsets of the unit cube
A Szemerédi-type theorem for subsets of the unit cubeVjekoslavKovac1
 
Estimates for a class of non-standard bilinear multipliers
Estimates for a class of non-standard bilinear multipliersEstimates for a class of non-standard bilinear multipliers
Estimates for a class of non-standard bilinear multipliersVjekoslavKovac1
 
Density theorems for anisotropic point configurations
Density theorems for anisotropic point configurationsDensity theorems for anisotropic point configurations
Density theorems for anisotropic point configurationsVjekoslavKovac1
 

Tendances (20)

Bayes Independence Test
Bayes Independence TestBayes Independence Test
Bayes Independence Test
 
Bellman functions and Lp estimates for paraproducts
Bellman functions and Lp estimates for paraproductsBellman functions and Lp estimates for paraproducts
Bellman functions and Lp estimates for paraproducts
 
Multilinear Twisted Paraproducts
Multilinear Twisted ParaproductsMultilinear Twisted Paraproducts
Multilinear Twisted Paraproducts
 
Multilinear singular integrals with entangled structure
Multilinear singular integrals with entangled structureMultilinear singular integrals with entangled structure
Multilinear singular integrals with entangled structure
 
Scattering theory analogues of several classical estimates in Fourier analysis
Scattering theory analogues of several classical estimates in Fourier analysisScattering theory analogues of several classical estimates in Fourier analysis
Scattering theory analogues of several classical estimates in Fourier analysis
 
A Generalization of the Chow-Liu Algorithm and its Applications to Artificial...
A Generalization of the Chow-Liu Algorithm and its Applications to Artificial...A Generalization of the Chow-Liu Algorithm and its Applications to Artificial...
A Generalization of the Chow-Liu Algorithm and its Applications to Artificial...
 
Bayesian regression models and treed Gaussian process models
Bayesian regression models and treed Gaussian process modelsBayesian regression models and treed Gaussian process models
Bayesian regression models and treed Gaussian process models
 
A Generalization of Nonparametric Estimation and On-Line Prediction for Stati...
A Generalization of Nonparametric Estimation and On-Line Prediction for Stati...A Generalization of Nonparametric Estimation and On-Line Prediction for Stati...
A Generalization of Nonparametric Estimation and On-Line Prediction for Stati...
 
A Conjecture on Strongly Consistent Learning
A Conjecture on Strongly Consistent LearningA Conjecture on Strongly Consistent Learning
A Conjecture on Strongly Consistent Learning
 
A sharp nonlinear Hausdorff-Young inequality for small potentials
A sharp nonlinear Hausdorff-Young inequality for small potentialsA sharp nonlinear Hausdorff-Young inequality for small potentials
A sharp nonlinear Hausdorff-Young inequality for small potentials
 
S.Duplij, A q-deformed generalization of the Hosszu-Gluskin theorem
S.Duplij, A q-deformed generalization of the Hosszu-Gluskin theoremS.Duplij, A q-deformed generalization of the Hosszu-Gluskin theorem
S.Duplij, A q-deformed generalization of the Hosszu-Gluskin theorem
 
Tales on two commuting transformations or flows
Tales on two commuting transformations or flowsTales on two commuting transformations or flows
Tales on two commuting transformations or flows
 
Paraproducts with general dilations
Paraproducts with general dilationsParaproducts with general dilations
Paraproducts with general dilations
 
A T(1)-type theorem for entangled multilinear Calderon-Zygmund operators
A T(1)-type theorem for entangled multilinear Calderon-Zygmund operatorsA T(1)-type theorem for entangled multilinear Calderon-Zygmund operators
A T(1)-type theorem for entangled multilinear Calderon-Zygmund operators
 
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
 
A Szemeredi-type theorem for subsets of the unit cube
A Szemeredi-type theorem for subsets of the unit cubeA Szemeredi-type theorem for subsets of the unit cube
A Szemeredi-type theorem for subsets of the unit cube
 
(DL hacks輪読) Deep Kernel Learning
(DL hacks輪読) Deep Kernel Learning(DL hacks輪読) Deep Kernel Learning
(DL hacks輪読) Deep Kernel Learning
 
A Szemerédi-type theorem for subsets of the unit cube
A Szemerédi-type theorem for subsets of the unit cubeA Szemerédi-type theorem for subsets of the unit cube
A Szemerédi-type theorem for subsets of the unit cube
 
Estimates for a class of non-standard bilinear multipliers
Estimates for a class of non-standard bilinear multipliersEstimates for a class of non-standard bilinear multipliers
Estimates for a class of non-standard bilinear multipliers
 
Density theorems for anisotropic point configurations
Density theorems for anisotropic point configurationsDensity theorems for anisotropic point configurations
Density theorems for anisotropic point configurations
 

En vedette

香港經濟日報: 企業宣傳新策:博低頭族一Like 20130923
香港經濟日報: 企業宣傳新策:博低頭族一Like 20130923香港經濟日報: 企業宣傳新策:博低頭族一Like 20130923
香港經濟日報: 企業宣傳新策:博低頭族一Like 20130923Adams Company Limited
 
公開鍵暗号3: ナップザック暗号
公開鍵暗号3: ナップザック暗号公開鍵暗号3: ナップザック暗号
公開鍵暗号3: ナップザック暗号Joe Suzuki
 
公開鍵暗号(7): データ圧縮
公開鍵暗号(7): データ圧縮公開鍵暗号(7): データ圧縮
公開鍵暗号(7): データ圧縮Joe Suzuki
 
Ansys.结构有限元高级分析方法与范例应用
Ansys.结构有限元高级分析方法与范例应用Ansys.结构有限元高级分析方法与范例应用
Ansys.结构有限元高级分析方法与范例应用pboy123
 

En vedette (8)

香港六合彩
香港六合彩香港六合彩
香港六合彩
 
香港經濟日報: 企業宣傳新策:博低頭族一Like 20130923
香港經濟日報: 企業宣傳新策:博低頭族一Like 20130923香港經濟日報: 企業宣傳新策:博低頭族一Like 20130923
香港經濟日報: 企業宣傳新策:博低頭族一Like 20130923
 
WITMSE 2013
WITMSE 2013WITMSE 2013
WITMSE 2013
 
香港六合彩
香港六合彩香港六合彩
香港六合彩
 
公開鍵暗号3: ナップザック暗号
公開鍵暗号3: ナップザック暗号公開鍵暗号3: ナップザック暗号
公開鍵暗号3: ナップザック暗号
 
公開鍵暗号(7): データ圧縮
公開鍵暗号(7): データ圧縮公開鍵暗号(7): データ圧縮
公開鍵暗号(7): データ圧縮
 
Ansys.结构有限元高级分析方法与范例应用
Ansys.结构有限元高级分析方法与范例应用Ansys.结构有限元高级分析方法与范例应用
Ansys.结构有限元高级分析方法与范例应用
 
Kids Can Code
Kids Can CodeKids Can Code
Kids Can Code
 

Similaire à 2013 IEEE International Symposium on Information Theory

Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Valentin De Bortoli
 
Basic math including gradient
Basic math including gradientBasic math including gradient
Basic math including gradientRamesh Kesavan
 
Lecture 2: linear SVM in the dual
Lecture 2: linear SVM in the dualLecture 2: linear SVM in the dual
Lecture 2: linear SVM in the dualStéphane Canu
 
Lecture 2: linear SVM in the Dual
Lecture 2: linear SVM in the DualLecture 2: linear SVM in the Dual
Lecture 2: linear SVM in the DualStéphane Canu
 
Improved Trainings of Wasserstein GANs (WGAN-GP)
Improved Trainings of Wasserstein GANs (WGAN-GP)Improved Trainings of Wasserstein GANs (WGAN-GP)
Improved Trainings of Wasserstein GANs (WGAN-GP)Sangwoo Mo
 
5.2 primitive recursive functions
5.2 primitive recursive functions5.2 primitive recursive functions
5.2 primitive recursive functionsSampath Kumar S
 
An Approach For Solving Nonlinear Programming Problems
An Approach For Solving Nonlinear Programming ProblemsAn Approach For Solving Nonlinear Programming Problems
An Approach For Solving Nonlinear Programming ProblemsMary Montoya
 
Automatic Bayesian method for Numerical Integration
Automatic Bayesian method for Numerical Integration Automatic Bayesian method for Numerical Integration
Automatic Bayesian method for Numerical Integration Jagadeeswaran Rathinavel
 
Probability cheatsheet
Probability cheatsheetProbability cheatsheet
Probability cheatsheetSuvrat Mishra
 
Finance Enginering from Columbia.pdf
Finance Enginering from Columbia.pdfFinance Enginering from Columbia.pdf
Finance Enginering from Columbia.pdfCarlosLazo45
 
Probability cheatsheet
Probability cheatsheetProbability cheatsheet
Probability cheatsheetJoachim Gwoke
 
Divergence clustering
Divergence clusteringDivergence clustering
Divergence clusteringFrank Nielsen
 
Parallel Bayesian Optimization
Parallel Bayesian OptimizationParallel Bayesian Optimization
Parallel Bayesian OptimizationSri Ambati
 
Hyperfunction method for numerical integration and Fredholm integral equation...
Hyperfunction method for numerical integration and Fredholm integral equation...Hyperfunction method for numerical integration and Fredholm integral equation...
Hyperfunction method for numerical integration and Fredholm integral equation...HidenoriOgata
 
Statistical Inference Part II: Types of Sampling Distribution
Statistical Inference Part II: Types of Sampling DistributionStatistical Inference Part II: Types of Sampling Distribution
Statistical Inference Part II: Types of Sampling DistributionDexlab Analytics
 
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...Tomoya Murata
 

Similaire à 2013 IEEE International Symposium on Information Theory (20)

Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...
 
Basic math including gradient
Basic math including gradientBasic math including gradient
Basic math including gradient
 
Lecture 2: linear SVM in the dual
Lecture 2: linear SVM in the dualLecture 2: linear SVM in the dual
Lecture 2: linear SVM in the dual
 
Lecture 2: linear SVM in the Dual
Lecture 2: linear SVM in the DualLecture 2: linear SVM in the Dual
Lecture 2: linear SVM in the Dual
 
Improved Trainings of Wasserstein GANs (WGAN-GP)
Improved Trainings of Wasserstein GANs (WGAN-GP)Improved Trainings of Wasserstein GANs (WGAN-GP)
Improved Trainings of Wasserstein GANs (WGAN-GP)
 
5.2 primitive recursive functions
5.2 primitive recursive functions5.2 primitive recursive functions
5.2 primitive recursive functions
 
An Approach For Solving Nonlinear Programming Problems
An Approach For Solving Nonlinear Programming ProblemsAn Approach For Solving Nonlinear Programming Problems
An Approach For Solving Nonlinear Programming Problems
 
QMC: Operator Splitting Workshop, Stochastic Block-Coordinate Fixed Point Alg...
QMC: Operator Splitting Workshop, Stochastic Block-Coordinate Fixed Point Alg...QMC: Operator Splitting Workshop, Stochastic Block-Coordinate Fixed Point Alg...
QMC: Operator Splitting Workshop, Stochastic Block-Coordinate Fixed Point Alg...
 
Probability Cheatsheet.pdf
Probability Cheatsheet.pdfProbability Cheatsheet.pdf
Probability Cheatsheet.pdf
 
Automatic Bayesian method for Numerical Integration
Automatic Bayesian method for Numerical Integration Automatic Bayesian method for Numerical Integration
Automatic Bayesian method for Numerical Integration
 
Probability cheatsheet
Probability cheatsheetProbability cheatsheet
Probability cheatsheet
 
Finance Enginering from Columbia.pdf
Finance Enginering from Columbia.pdfFinance Enginering from Columbia.pdf
Finance Enginering from Columbia.pdf
 
Probability cheatsheet
Probability cheatsheetProbability cheatsheet
Probability cheatsheet
 
Divergence clustering
Divergence clusteringDivergence clustering
Divergence clustering
 
Parallel Bayesian Optimization
Parallel Bayesian OptimizationParallel Bayesian Optimization
Parallel Bayesian Optimization
 
ma112011id535
ma112011id535ma112011id535
ma112011id535
 
Hyperfunction method for numerical integration and Fredholm integral equation...
Hyperfunction method for numerical integration and Fredholm integral equation...Hyperfunction method for numerical integration and Fredholm integral equation...
Hyperfunction method for numerical integration and Fredholm integral equation...
 
Statistical Inference Part II: Types of Sampling Distribution
Statistical Inference Part II: Types of Sampling DistributionStatistical Inference Part II: Types of Sampling Distribution
Statistical Inference Part II: Types of Sampling Distribution
 
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...
 
QMC: Operator Splitting Workshop, A Splitting Method for Nonsmooth Nonconvex ...
QMC: Operator Splitting Workshop, A Splitting Method for Nonsmooth Nonconvex ...QMC: Operator Splitting Workshop, A Splitting Method for Nonsmooth Nonconvex ...
QMC: Operator Splitting Workshop, A Splitting Method for Nonsmooth Nonconvex ...
 

Plus de Joe Suzuki

RとPythonを比較する
RとPythonを比較するRとPythonを比較する
RとPythonを比較するJoe Suzuki
 
R集会@統数研
R集会@統数研R集会@統数研
R集会@統数研Joe Suzuki
 
E-learning Development of Statistics and in Duex: Practical Approaches and Th...
E-learning Development of Statistics and in Duex: Practical Approaches and Th...E-learning Development of Statistics and in Duex: Practical Approaches and Th...
E-learning Development of Statistics and in Duex: Practical Approaches and Th...Joe Suzuki
 
分枝限定法でモデル選択の計算量を低減する
分枝限定法でモデル選択の計算量を低減する分枝限定法でモデル選択の計算量を低減する
分枝限定法でモデル選択の計算量を低減するJoe Suzuki
 
連続変量を含む条件付相互情報量の推定
連続変量を含む条件付相互情報量の推定連続変量を含む条件付相互情報量の推定
連続変量を含む条件付相互情報量の推定Joe Suzuki
 
E-learning Design and Development for Data Science in Osaka University
E-learning Design and Development for Data Science in Osaka UniversityE-learning Design and Development for Data Science in Osaka University
E-learning Design and Development for Data Science in Osaka UniversityJoe Suzuki
 
AMBN2017 サテライトワークショップ
AMBN2017 サテライトワークショップAMBN2017 サテライトワークショップ
AMBN2017 サテライトワークショップJoe Suzuki
 
CRAN Rパッケージ BNSLの概要
CRAN Rパッケージ BNSLの概要CRAN Rパッケージ BNSLの概要
CRAN Rパッケージ BNSLの概要Joe Suzuki
 
Forest Learning from Data
Forest Learning from DataForest Learning from Data
Forest Learning from DataJoe Suzuki
 
A Bayesian Approach to Data Compression
A Bayesian Approach to Data CompressionA Bayesian Approach to Data Compression
A Bayesian Approach to Data CompressionJoe Suzuki
 
研究紹介(学生向け)
研究紹介(学生向け)研究紹介(学生向け)
研究紹介(学生向け)Joe Suzuki
 
Bayesian network structure estimation based on the Bayesian/MDL criteria when...
Bayesian network structure estimation based on the Bayesian/MDL criteria when...Bayesian network structure estimation based on the Bayesian/MDL criteria when...
Bayesian network structure estimation based on the Bayesian/MDL criteria when...Joe Suzuki
 
The Universal Bayesian Chow-Liu Algorithm
The Universal Bayesian Chow-Liu AlgorithmThe Universal Bayesian Chow-Liu Algorithm
The Universal Bayesian Chow-Liu AlgorithmJoe Suzuki
 
Efficietly Learning Bayesian Network Structures based on the B&B Strategy: A ...
Efficietly Learning Bayesian Network Structuresbased on the B&B Strategy: A ...Efficietly Learning Bayesian Network Structuresbased on the B&B Strategy: A ...
Efficietly Learning Bayesian Network Structures based on the B&B Strategy: A ...Joe Suzuki
 
Forest Learning based on the Chow-Liu Algorithm and its Application to Genom...
Forest Learning based on the Chow-Liu Algorithm and its Application to Genom...Forest Learning based on the Chow-Liu Algorithm and its Application to Genom...
Forest Learning based on the Chow-Liu Algorithm and its Application to Genom...Joe Suzuki
 
Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...
Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...
Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...Joe Suzuki
 
連続変量を含む相互情報量の推定
連続変量を含む相互情報量の推定連続変量を含む相互情報量の推定
連続変量を含む相互情報量の推定Joe Suzuki
 
Jeffreys' and BDeu Priors for Model Selection
Jeffreys' and BDeu Priors for Model SelectionJeffreys' and BDeu Priors for Model Selection
Jeffreys' and BDeu Priors for Model SelectionJoe Suzuki
 

Plus de Joe Suzuki (20)

RとPythonを比較する
RとPythonを比較するRとPythonを比較する
RとPythonを比較する
 
R集会@統数研
R集会@統数研R集会@統数研
R集会@統数研
 
E-learning Development of Statistics and in Duex: Practical Approaches and Th...
E-learning Development of Statistics and in Duex: Practical Approaches and Th...E-learning Development of Statistics and in Duex: Practical Approaches and Th...
E-learning Development of Statistics and in Duex: Practical Approaches and Th...
 
分枝限定法でモデル選択の計算量を低減する
分枝限定法でモデル選択の計算量を低減する分枝限定法でモデル選択の計算量を低減する
分枝限定法でモデル選択の計算量を低減する
 
連続変量を含む条件付相互情報量の推定
連続変量を含む条件付相互情報量の推定連続変量を含む条件付相互情報量の推定
連続変量を含む条件付相互情報量の推定
 
E-learning Design and Development for Data Science in Osaka University
E-learning Design and Development for Data Science in Osaka UniversityE-learning Design and Development for Data Science in Osaka University
E-learning Design and Development for Data Science in Osaka University
 
UAI 2017
UAI 2017UAI 2017
UAI 2017
 
AMBN2017 サテライトワークショップ
AMBN2017 サテライトワークショップAMBN2017 サテライトワークショップ
AMBN2017 サテライトワークショップ
 
CRAN Rパッケージ BNSLの概要
CRAN Rパッケージ BNSLの概要CRAN Rパッケージ BNSLの概要
CRAN Rパッケージ BNSLの概要
 
Forest Learning from Data
Forest Learning from DataForest Learning from Data
Forest Learning from Data
 
A Bayesian Approach to Data Compression
A Bayesian Approach to Data CompressionA Bayesian Approach to Data Compression
A Bayesian Approach to Data Compression
 
研究紹介(学生向け)
研究紹介(学生向け)研究紹介(学生向け)
研究紹介(学生向け)
 
Bayesian network structure estimation based on the Bayesian/MDL criteria when...
Bayesian network structure estimation based on the Bayesian/MDL criteria when...Bayesian network structure estimation based on the Bayesian/MDL criteria when...
Bayesian network structure estimation based on the Bayesian/MDL criteria when...
 
The Universal Bayesian Chow-Liu Algorithm
The Universal Bayesian Chow-Liu AlgorithmThe Universal Bayesian Chow-Liu Algorithm
The Universal Bayesian Chow-Liu Algorithm
 
Efficietly Learning Bayesian Network Structures based on the B&B Strategy: A ...
Efficietly Learning Bayesian Network Structuresbased on the B&B Strategy: A ...Efficietly Learning Bayesian Network Structuresbased on the B&B Strategy: A ...
Efficietly Learning Bayesian Network Structures based on the B&B Strategy: A ...
 
Forest Learning based on the Chow-Liu Algorithm and its Application to Genom...
Forest Learning based on the Chow-Liu Algorithm and its Application to Genom...Forest Learning based on the Chow-Liu Algorithm and its Application to Genom...
Forest Learning based on the Chow-Liu Algorithm and its Application to Genom...
 
2016 7-13
2016 7-132016 7-13
2016 7-13
 
Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...
Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...
Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...
 
連続変量を含む相互情報量の推定
連続変量を含む相互情報量の推定連続変量を含む相互情報量の推定
連続変量を含む相互情報量の推定
 
Jeffreys' and BDeu Priors for Model Selection
Jeffreys' and BDeu Priors for Model SelectionJeffreys' and BDeu Priors for Model Selection
Jeffreys' and BDeu Priors for Model Selection
 

Dernier

Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piececharlottematthew16
 
From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .Alan Dix
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxhariprasad279825
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brandgvaughan
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxLoriGlavin3
 
DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenDevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenHervé Boutemy
 
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DayH2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DaySri Ambati
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr BaganFwdays
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity PlanDatabarracks
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfAddepto
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Manik S Magar
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupFlorian Wilhelm
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 

Dernier (20)

Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piece
 
From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptx
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brand
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
 
DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenDevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache Maven
 
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DayH2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity Plan
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdf
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project Setup
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 

2013 IEEE International Symposium on Information Theory

  • 1. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary Universal Bayesian Measures Joe Suzuki Osaka University IEEE International Symposium on Information Theory Istanbul, Turky July 8, 2013 1 / 19 Universal Bayesian Measures
  • 2. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary Given n examples, identify whether X, Y are independent or not (x1, y1), · · · , (xn, yn) ∼ (X, Y ) ∈ {0, 1} × {0, 1} p: a prior probability that X, Y are independent The Bayesian answer Consider weight W over θ to compute Qn (xn ) := ∫ P(xn |θ)dW (θ) , Qn (yn ) := ∫ P(yn |θ)dW (θ) Qn (xn , yn ) := ∫ P(xn , yn |θ)dW (θ) pQn(xn)Qn(yn) ≥ (1 − p)Qn(xn, yn) ⇐⇒ X, Y are independent 2 / 19 Universal Bayesian Measures
  • 3. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary Problem: what if X, Y are arbitrary random variables? (Ω, F, P): probability space B: the Borel set of R   X is a random variable . . X : Ω → R is F-measurable (D ∈ B =⇒ {ω ∈ Ω|X(ω) ∈ D} ∈ F)   X, Y may be either discrete contunuous none of them 3 / 19 Universal Bayesian Measures
  • 4. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary What Qn is qualified to be an alternative to Pn ? True θ = θ∗ is not available . . Pn(xn) = P(xn|θ∗), Pn(yn) = P(yn|θ∗) Pn(xn, yn) = Pn(xn, yn|θ∗) Qn (xn ) := ∫ P(xn |θ)dW (θ) , Qn (yn ) := ∫ P(yn |θ)dW (θ) Qn (xn , yn ) := ∫ P(xn , yn |θ)dW (θ) 4 / 19 Universal Bayesian Measures
  • 5. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary Example: Bayes Codes c: the # of ones in xn θ: the prob. of ones P(xn |θ) = θc (1 − θ)n−c a, b > 0 w(θ) ∝ 1 θa(1 − θ)b   For each xn = (x1, · · · , xn) ∈ {0, 1}n, Qn (xn ) := ∫ w(θ)P(xn |θ)dθ = ∏c−1 j=0 (j + a) · ∏n−c−1 k=0 (k + b) ∏n−1 i=0 (i + a + b) 5 / 19 Universal Bayesian Measures
  • 6. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary Universal Coding/Measures If we choose a = b = 1/2 (Krichevsky-Trofimov) and xn is i.i.d. emitted by Pn (xn |θ) = n∏ i=1 P(xi ) , P(xi ) = θ, 1 − θ then, for any P, almost surely, − 1 n log Qn (xn ) → H := ∑ x∈A −P(x) log P(x) From Shannon McMillian Breiman, for any P, − 1 n log Pn (xn |θ) = 1 n n∑ i=1 − log P(xi ) → E[− log P(xi )] = H 6 / 19 Universal Bayesian Measures
  • 7. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary Why Pn can be replaced by Qn if n is large ? For any P, almost surely, 1 n log Pn(xn) Qn(xn) → 0 (1) Qn: a universal Bayesian measure for A . What are Qn and (1) in the general settings ? 7 / 19 Universal Bayesian Measures
  • 8. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary Suppose a density function exists for X A: the range of X A0 := {A} Aj+1 is a refinement of Aj Example 1: if A = [0, 1), the sequence can be A0 = {[0, 1)}, A1 = {[0, 1/2), [1/2, 1)} A2 = {[0, 1/4), [1/4, 1/2), [1/2, 3/4), [3/4, 1)} . . . Aj = {[0, 2−(j−1)), [2−(j−1), 2 · 2−(j−1)), · · · , [(2j−1 − 1)2−(j−1), 1)} . . . sj : A → Aj (quantization, x ∈ a ∈ Aj =⇒ sj (x) = a) λ : R → B (Lebesgue measure, a = [b, c) =⇒ λ(a) = c − b) Qn j : a universal Bayesian measure for Aj 8 / 19 Universal Bayesian Measures
  • 9. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary If (sj (x1), · · · , sj (xn)) = (a1, · · · , an), gn j (xn ) := Qn j (a1, · · · , an) λ(a1) · · · λ(an) f n j (xn ) := fj (x1) · · · fj (xn) = Pj (a1) · · · Pj (an) λ(a1) . . . λ(an) For {ωj }∞ j=1: ∑ ωj = 1, ωj > 0, gn (xn ) := ∞∑ j=1 ωj gn j (xn ) For any f and {Aj } s.t. h(fj ) → h(f ) as j → ∞, almost surely 1 n log f n(xn) gn(xn) → 0 (2) B. Ryabko. IEEE Trans. on Inform. Theory, 55, 9, 2009. 9 / 19 Universal Bayesian Measures
  • 10. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary Our Goal: what are they generalized into? . 1 if the random variable takes finite values: 1 n log Pn (xn ) Qn(xn) → 0 (1) for any Pn . 2 if a density function exists: 1 n log f n (xn ) gn(xn) → 0 (2) for any f n and {Aj } satisfies h(fj ) → h(f ) as j → ∞ 10 / 19 Universal Bayesian Measures
  • 11. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary Exactly when does density function exist? B: the Borel sets of R µ(D): the prob. of D ∈ B When a density function exists . The following are equivalent (µ ≪ λ): for each D ∈ B, λ(D) = 0 =⇒ µ(D) = 0 ∃ B-measurable dµ dλ := f s.t. µ(D) = ∫ D f (t)dλ(t) f is the density function (w.r.t. λ). 11 / 19 Universal Bayesian Measures
  • 12. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary Density Functions in a General Sense Radon-Nikodum’s Theorem . . The following are equivalent (µ ≪ η): for each D ∈ B, η(D) = 0 =⇒ µ(D) = 0 ∃ B-measurable dµ dη := fη s.t. µ(D) = ∫ D fη(t)dη(t) fη is the density function w.r.t. η.   Example 2: µ({h}) > 0, η({h}) := 1 h(h + 1) , h ∈ B := {1, 2, · · · } µ ≪ η µ(D) = ∑ h∈D∩B fη(h)η({h}) dµ dη (h) = fη(h) = µ({h}) η({h}) = h(h + 1)µ({h}) 12 / 19 Universal Bayesian Measures
  • 13. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary B1 := {{1}, {2, 3, · · · }} B2 := {{1}, {2}, {3, 4, · · · }} . . . Bk := {{1}, {2}, · · · , {k}, {k + 1, k + 2, · · · }} . . . tk : B → Bk (quantization, y ∈ b ∈ Bk =⇒ tk(y) = b) If (tk(y1), · · · , tk(yn)) = (b1, · · · , bn), gn η,k(yn ) := Qn k (b1, · · · , bn) η(b1) · · · η(bn) , gn η (yn ) := ∞∑ k=1 ωkgn η,k(yn ) For any fη and {Bk} s.t. h(fη,k) → h(fη) , almost surely 1 n log f n η (yn) gn η (yn) → 0 (3) gn(yn) ∏n i=1 ηn({yi }) estimates P(yn) = f n η (yn) ∏n i=1 ηn({yi }) 13 / 19 Universal Bayesian Measures
  • 14. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary In the general case µn (Dn ) := ∫ D f n η (yn )dηn (yn ) νn (Dn ) := ∫ D gn η (yn )dηn (yn ) f n η (yn) gn η (yn) = dµn dηn (yn )/ dνn dηn (yn ) = dµn dνn (yn ) D(µ||ν) := ∫ dµ log dµ dν h(fη) := ∫ −f n η (yn ) log f n η (yn )dη(yn ) = − ∫ dµ dη (yn ) log dµ dη (yn ) · dη(yn ) = −D(µ||η) 14 / 19 Universal Bayesian Measures
  • 15. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary Main Theorem Theorem . With probability one as n → ∞ 1 n log dµn dνn (yn ) → 0 for any stationary ergodic µn and {Bk} such that D(µk||η) → D(µ||η) as k → ∞ 15 / 19 Universal Bayesian Measures
  • 16. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary Joint Density Functions Example 3: A × B (based on Examples 1,2) µ ≪ λη A0 × B0 = {A} × {B} = {[0, 1)} × {{1, 2, · · · }} A1 × B1 A2 × B2 . . . Aj × Bk . . . (sj , tk) : A × B → Aj × Bk   If {Aj × Bk} satisfies fλη,jk → fλη, for any fλη, almost surely, we can construct gn λη s.t. 1 n log f n λη(xn, yn) gn λη(xn, yn) → 0 (4) 16 / 19 Universal Bayesian Measures
  • 17. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary The Answer to the Problem Estimate f n X (xn), f n Y (yn), f n XY (xn, yn) by gn X (xn), gn Y (yn), gn XY (xn, yn)   The Bayesian answer . . pgn X (xn)gn Y (yn) ≤ (1 − p)gXY (xn, yn) ⇐⇒ X, Y are independent 17 / 19 Universal Bayesian Measures
  • 18. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary The General Bayesian Solution Givem n examples zn and prior {pm} over models m = 1, 2, · · · , compute gn (zn |m) for each m = 1, 2, · · · find the model m maxmizing pmg(zn |m) 18 / 19 Universal Bayesian Measures
  • 19. Problem Density Functions Generalized Density Functions The Bayesian Solution Summary Summary and Discussion Bayesian Measure . . Generalization without assuming Discrete or Continuous Universality of Bayes/MDL in the generalized sense Many Applications Bayesian network structure estimation (DCC 2012) The Bayesian Chow-Liu Algorithm (PGM 2012) Markov order estimation even when {Xi } is continuous 19 / 19 Universal Bayesian Measures