SlideShare une entreprise Scribd logo
BB
UATOIN
HOUSE	SEMINAR
ber,	2nd,	2017
aishu MINAMI
Research of Rate-Distortion theory
and Variational Auto-encoders
Presentation: 37 (@_1_137)
Date: Dec 15th, 2019 11:00~12:00
Place: Kernel Hongo
Overview
• Intro. of Rate-Distortion Theory
- Elements of Information Theory, Thomas M. Cover, Joy A. Thomas (1991)
• Bridge of Rate-Distortion theory and VAE
- Fixing a Broken ELBO (Alemi+ ICML 2018)
• Rate-Distortion theory and Memory distortion in humans (for coffee break)
- An experimental study of the effect of language on the reproduction of visually
perceived forms (Carmichael+ 1932)
- Semantic Compression of Episodic Memories (Nagy+ 2018)
• Recent research
- Exact Rate-Distortion in Autoencoders via Echo Noise (Brekelmans+ NIPS 2019)
Rate-Distortion Theory
• This theory can state as follows:
- Given a source distribution and a distortion measure,
what is the minimum expected distortion achievable at a particular rate?
- Or, what is the minimum rate required to achieve a particular distortion?
R(D) = min
p( ̂x|x):p(x)p( ̂x|x)d(x, ̂x)≤D
I(X, ̂X)
X →
Y=f(X)
→ ̂XEncoder Decoder
• Rate-Distortion theory:
- created by Claude Shannon in 1948 in famous paper:
“A Mathematical Theory of Communication”
- We’d like to care about the mutual information MI(X, X’) and distortion D(X, X’)
- Rate: the number of bits per data sample to be stored or transmitted
- Distortion: the difference between input and output signal
Elements	of	Informa.on	Theory,	Thomas	M.	Cover,	Joy	A.	Thomas
Examples of Rate Distortion curves
a N(0, σ2) source with squared error distortion
R(D) =
{
1
2
log
σ2
D
, 0 ≤ D ≤ σ2
0 σ2
≤ D
Test channel
̂X ∼ N(0,σ2
− D)
Z ∼ N(0,D)
X ∼ N(0,σ2
)
a Bernoulli(p) source with Hamming distortion
R(D) =
{
H(p) − H(D), 0 ≤ D ≤ min{p,1 − p}
0 D > min{p,1 − p}
Test channel
1 − D
1 − D
D
D
̂X X
1 − p
r p
1 − r
Elements	of	Informa.on	Theory,	Thomas	M.	Cover,	Joy	A.	Thomas
Fixing a Broken ELBO
Alexander A. Alemi, Ben Poole, Ian Fischer, Joshua V. Dillon, Rif A. Saurous, Kevin Murphy, ICML 2018
Alemi, A., Poole, B., Fischer, I., Dillon, J., Saurous, R., Murphy, K. (2017). Fixing a Broken ELBOhttps://arxiv.org/abs/1711.00464
β-VAE Loss function
Testing RD-curve in several models (e,d,m):
: simple or complex encoder
: simple or complex decoder
: simple, complex, or Vamp
e ∈ { − , + }
d ∈ { − , + }
m ∈ { − , + ,v}
Definition
An experimental study of the effect of language on the reproduction of visually perceived forms
• History:
✓ G. E. Müller, Zur Analyse der Gedächtnistätigkeit und des Vorstellungsverlaufes (1913)
(For analysis of memory activity and the Mousse of ideas, translated by google)
✴ The reproduction changes after the passage of time
✓ F. Wulf, Über die Veränderung von Vorstellungen (Gedächtnis und Gestalt)
in (1921) (changing ideas, translated by google)
✴ The identification involves the linguistic naming of the objects
• Carmichael et al. reported the reproduction of visually perceived form by the use of
language
• Experiment: At first, the participants (60 subjects) received the stimulus figures with word list 1
or 2. assigned. Then, they reproduce the visual forms on each category.
L. Carmichael, H. P. Hogan, A. A. Walter (1932)
Carmichael, L., Hogan, H., Walter, A. (1932). An experimental study of the effect of language on the reproduction of visually perceived form. Journal of Experimental Psychology 15(1), 73. https://
dx.doi.org/10.1037/h0072671
An experimental study of the effect of language on the reproduction of visually perceived forms
• Result: Linguistic label distorts the memory and visual forms
L. Carmichael, H. P. Hogan, A. A. Walter (1932)
Carmichael, L., Hogan, H., Walter, A. (1932). An experimental study of the effect of language on the reproduction of visually perceived form. Journal of Experimental Psychology 15(1), 73. https://
dx.doi.org/10.1037/h0072671
Semantic Compression of Episodic Memories
• The relevance of RDT for explaining errors and biases in human visual working memory
• Result below shows the reconstruction at different rates (changed value of β)
David G. Nagy, Balazs Török, Gergõ Orbán (2018)
Nagy, D., Török, B., Orbán, G. (2018). Semantic Compression of Episodic Memorieshttps://arxiv.org/abs/1806.07990
• Idea:
✓ Let’s determine the noise in a data-driven fashion which doesn’t require restrictive prior
distributional assumptions
• Result:
✓ the model provided the exact expression for mutual information and outperformed flow-
based method without the need to train additional distributional transformations
• Losses:
✓ VAE Loss:
✓
Echo noise:
• Echo noise properties:
1. z has the same distribution as
2. The mutual information
is as follows:
q(z|x) = μ(x) + σ(x)ϵ, ϵ ∼ N(0,I)
q(z|x) = μ(x) + σ(x)ϵ(x), ϵ =
∞
∑
l=0
(Πl
l′=1σ(xl′
))μ(xl
), xl
∼ q(x)
ϵ
I(X; Z) = − E log|detσ(x)|
Exact Rate-Distortion in Autoencoders via Echo Noise
Rob Brekelmans, Daniel Moyer, Aram Galstyan, Greg Ver Steeg, NIPS 2019
Brekelmans, R., Moyer, D., Galstyan, A., Steeg, G. (2019). Exact Rate-Distortion in Autoencoders via Echo Noisehttps://arxiv.org/abs/1904.07199
Illustration of setting μ(x) = x, σ(x) = 0.5
• How do we derive the echo noise?
✓ We’d like to choose the noise to enforce an equivalence between the distributions
q(z) and q(ε) for mutual information computation
✓ ,
✓ Let’s make the noise match the channel output:
✓
✓ We can guarantee that the noise and marginal distributions match in the limit
• Lossy Compression in VAEs
✓ ELBO
✓ KL term
• Rate-Distortion Objective
q(z) =
∫
qϕ(z|x)q(x)dx qϕ(z|x) = μ(x) + σ(x)ϵ
ϵ = μ(x′), x′ ∼ q(x)
ϵ = μ(x0
) + σ(x0
)(μ(x1
) + σ(x1
)(μ(x2
) + σ(x2
) . . .
Exact Rate-Distortion in Autoencoders via Echo Noise
Rob Brekelmans, Daniel Moyer, Aram Galstyan, Greg Ver Steeg, NIPS 2019
Brekelmans, R., Moyer, D., Galstyan, A., Steeg, G. (2019). Exact Rate-Distortion in Autoencoders via Echo Noisehttps://arxiv.org/abs/1904.07199
• At low rates, Echo maintain only high level features of the input image
• At high rates, Echo gives the better reconstruction error than Info VA
Exact Rate-Distortion in Autoencoders via Echo Noise
Rob Brekelmans, Daniel Moyer, Aram Galstyan, Greg Ver Steeg, NIPS 2019
Brekelmans, R., Moyer, D., Galstyan, A., Steeg, G. (2019). Exact Rate-Distortion in Autoencoders via Echo Noisehttps://arxiv.org/abs/1904.07199

Contenu connexe

Tendances

Digital image processing
Digital image processingDigital image processing
Digital image processing
ABIRAMI M
 
Image denoising
Image denoising Image denoising
Image denoising
umarjamil10000
 
[NeuralIPS 2020]filter in filter pruning
[NeuralIPS 2020]filter in filter pruning[NeuralIPS 2020]filter in filter pruning
[NeuralIPS 2020]filter in filter pruning
KIMMINHA3
 
Single image haze removal
Single image haze removalSingle image haze removal
Single image haze removal
MohsinGhazi2
 
GAN - Theory and Applications
GAN - Theory and ApplicationsGAN - Theory and Applications
GAN - Theory and Applications
Emanuele Ghelfi
 
Digital Image Processing
Digital Image ProcessingDigital Image Processing
Digital Image Processing
lalithambiga kamaraj
 
06 spatial filtering DIP
06 spatial filtering DIP06 spatial filtering DIP
06 spatial filtering DIP
babak danyal
 
Masked Autoencoders Are Scalable Vision Learners.pptx
Masked Autoencoders Are Scalable Vision Learners.pptxMasked Autoencoders Are Scalable Vision Learners.pptx
Masked Autoencoders Are Scalable Vision Learners.pptx
Sangmin Woo
 
Lecture 12
Lecture 12Lecture 12
Lecture 12
Wael Sharba
 
Latent Dirichlet Allocation
Latent Dirichlet AllocationLatent Dirichlet Allocation
Latent Dirichlet Allocation
Sangwoo Mo
 
The motion estimation
The motion estimationThe motion estimation
The motion estimation
sakshij91
 
Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising without Cl...
Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising without Cl...Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising without Cl...
Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising without Cl...
KwanyoungKim7
 
Domain adaptation
Domain adaptationDomain adaptation
Domain adaptation
Tomoya Koike
 
Introduction of Faster R-CNN
Introduction of Faster R-CNNIntroduction of Faster R-CNN
Introduction of Faster R-CNN
Simossyi Funabashi
 
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
Universitat Politècnica de Catalunya
 
Image segmentation ppt
Image segmentation pptImage segmentation ppt
Image segmentation ppt
Gichelle Amon
 
Image segmentation with deep learning
Image segmentation with deep learningImage segmentation with deep learning
Image segmentation with deep learning
Antonio Rueda-Toicen
 
VVC tutorial at ICME 2020 together with Benjamin Bross
VVC tutorial at ICME 2020 together with Benjamin BrossVVC tutorial at ICME 2020 together with Benjamin Bross
VVC tutorial at ICME 2020 together with Benjamin Bross
Mathias Wien
 
Huffman Coding
Huffman CodingHuffman Coding
Huffman Coding
anithabalaprabhu
 
03.12 cnn backpropagation
03.12 cnn backpropagation03.12 cnn backpropagation
03.12 cnn backpropagation
Dea-hwan Ki
 

Tendances (20)

Digital image processing
Digital image processingDigital image processing
Digital image processing
 
Image denoising
Image denoising Image denoising
Image denoising
 
[NeuralIPS 2020]filter in filter pruning
[NeuralIPS 2020]filter in filter pruning[NeuralIPS 2020]filter in filter pruning
[NeuralIPS 2020]filter in filter pruning
 
Single image haze removal
Single image haze removalSingle image haze removal
Single image haze removal
 
GAN - Theory and Applications
GAN - Theory and ApplicationsGAN - Theory and Applications
GAN - Theory and Applications
 
Digital Image Processing
Digital Image ProcessingDigital Image Processing
Digital Image Processing
 
06 spatial filtering DIP
06 spatial filtering DIP06 spatial filtering DIP
06 spatial filtering DIP
 
Masked Autoencoders Are Scalable Vision Learners.pptx
Masked Autoencoders Are Scalable Vision Learners.pptxMasked Autoencoders Are Scalable Vision Learners.pptx
Masked Autoencoders Are Scalable Vision Learners.pptx
 
Lecture 12
Lecture 12Lecture 12
Lecture 12
 
Latent Dirichlet Allocation
Latent Dirichlet AllocationLatent Dirichlet Allocation
Latent Dirichlet Allocation
 
The motion estimation
The motion estimationThe motion estimation
The motion estimation
 
Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising without Cl...
Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising without Cl...Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising without Cl...
Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising without Cl...
 
Domain adaptation
Domain adaptationDomain adaptation
Domain adaptation
 
Introduction of Faster R-CNN
Introduction of Faster R-CNNIntroduction of Faster R-CNN
Introduction of Faster R-CNN
 
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
 
Image segmentation ppt
Image segmentation pptImage segmentation ppt
Image segmentation ppt
 
Image segmentation with deep learning
Image segmentation with deep learningImage segmentation with deep learning
Image segmentation with deep learning
 
VVC tutorial at ICME 2020 together with Benjamin Bross
VVC tutorial at ICME 2020 together with Benjamin BrossVVC tutorial at ICME 2020 together with Benjamin Bross
VVC tutorial at ICME 2020 together with Benjamin Bross
 
Huffman Coding
Huffman CodingHuffman Coding
Huffman Coding
 
03.12 cnn backpropagation
03.12 cnn backpropagation03.12 cnn backpropagation
03.12 cnn backpropagation
 

Similaire à 20191215 rate distortion theory and VAEs

Bioscientist Poster2
Bioscientist Poster2Bioscientist Poster2
Bioscientist Poster2
Karishma Daftary
 
A literature review on improving speech intelligibility in noisy environment
A literature review on improving speech intelligibility in noisy environmentA literature review on improving speech intelligibility in noisy environment
A literature review on improving speech intelligibility in noisy environment
OHSU | Oregon Health & Science University
 
More than Words: Advancing Prosodic Analysis
More than Words: Advancing Prosodic AnalysisMore than Words: Advancing Prosodic Analysis
129966864160453838[1]
129966864160453838[1]129966864160453838[1]
129966864160453838[1]
威華 王
 
Thesis
ThesisThesis
Thesis
joseangl
 
2022-10, UCL NLP meetup, Toward a Better Understanding of Relational Knowledg...
2022-10, UCL NLP meetup, Toward a Better Understanding of Relational Knowledg...2022-10, UCL NLP meetup, Toward a Better Understanding of Relational Knowledg...
2022-10, UCL NLP meetup, Toward a Better Understanding of Relational Knowledg...
asahiushio1
 
DYNAMIC PHONE WARPING – A METHOD TO MEASURE THE DISTANCE BETWEEN PRONUNCIATIONS
DYNAMIC PHONE WARPING – A METHOD TO MEASURE THE DISTANCE BETWEEN PRONUNCIATIONS DYNAMIC PHONE WARPING – A METHOD TO MEASURE THE DISTANCE BETWEEN PRONUNCIATIONS
DYNAMIC PHONE WARPING – A METHOD TO MEASURE THE DISTANCE BETWEEN PRONUNCIATIONS
cscpconf
 
Fol
FolFol
Incremental Difference as Feature for Lipreading
Incremental Difference as Feature for LipreadingIncremental Difference as Feature for Lipreading
Incremental Difference as Feature for Lipreading
IDES Editor
 
Adpositional Argumentation: How Logic Originates In Natural Argumentative Dis...
Adpositional Argumentation: How Logic Originates In Natural Argumentative Dis...Adpositional Argumentation: How Logic Originates In Natural Argumentative Dis...
Adpositional Argumentation: How Logic Originates In Natural Argumentative Dis...
Federico Gobbo
 
Slides: A glance at information-geometric signal processing
Slides: A glance at information-geometric signal processingSlides: A glance at information-geometric signal processing
Slides: A glance at information-geometric signal processing
Frank Nielsen
 
Techfest jan17
Techfest jan17Techfest jan17
Techfest jan17
Ramin Anushiravani
 
How do you know what I mean?: Psycholinguistics of spoken language communicat...
How do you know what I mean?: Psycholinguistics of spoken language communicat...How do you know what I mean?: Psycholinguistics of spoken language communicat...
How do you know what I mean?: Psycholinguistics of spoken language communicat...
ChigusaKurumada
 
Esa act
Esa actEsa act
ESR11 Hoang Cuong - EXPERT Summer School - Malaga 2015
ESR11 Hoang Cuong - EXPERT Summer School - Malaga 2015ESR11 Hoang Cuong - EXPERT Summer School - Malaga 2015
ESR11 Hoang Cuong - EXPERT Summer School - Malaga 2015
RIILP
 
Topic model an introduction
Topic model an introductionTopic model an introduction
Topic model an introduction
Yueshen Xu
 
Allerton
AllertonAllerton
Allerton
mustafa sarac
 
Unit 6: All
Unit 6: AllUnit 6: All
Unit 6: All
Hector Zenil
 
Writing the discussion chapter for quantitative research.pdf
Writing the discussion chapter for quantitative research.pdfWriting the discussion chapter for quantitative research.pdf
Writing the discussion chapter for quantitative research.pdf
Martin McMorrow
 
Speech To Sign Language Interpreter System
Speech To Sign Language Interpreter SystemSpeech To Sign Language Interpreter System
Speech To Sign Language Interpreter System
kkkseld
 

Similaire à 20191215 rate distortion theory and VAEs (20)

Bioscientist Poster2
Bioscientist Poster2Bioscientist Poster2
Bioscientist Poster2
 
A literature review on improving speech intelligibility in noisy environment
A literature review on improving speech intelligibility in noisy environmentA literature review on improving speech intelligibility in noisy environment
A literature review on improving speech intelligibility in noisy environment
 
More than Words: Advancing Prosodic Analysis
More than Words: Advancing Prosodic AnalysisMore than Words: Advancing Prosodic Analysis
More than Words: Advancing Prosodic Analysis
 
129966864160453838[1]
129966864160453838[1]129966864160453838[1]
129966864160453838[1]
 
Thesis
ThesisThesis
Thesis
 
2022-10, UCL NLP meetup, Toward a Better Understanding of Relational Knowledg...
2022-10, UCL NLP meetup, Toward a Better Understanding of Relational Knowledg...2022-10, UCL NLP meetup, Toward a Better Understanding of Relational Knowledg...
2022-10, UCL NLP meetup, Toward a Better Understanding of Relational Knowledg...
 
DYNAMIC PHONE WARPING – A METHOD TO MEASURE THE DISTANCE BETWEEN PRONUNCIATIONS
DYNAMIC PHONE WARPING – A METHOD TO MEASURE THE DISTANCE BETWEEN PRONUNCIATIONS DYNAMIC PHONE WARPING – A METHOD TO MEASURE THE DISTANCE BETWEEN PRONUNCIATIONS
DYNAMIC PHONE WARPING – A METHOD TO MEASURE THE DISTANCE BETWEEN PRONUNCIATIONS
 
Fol
FolFol
Fol
 
Incremental Difference as Feature for Lipreading
Incremental Difference as Feature for LipreadingIncremental Difference as Feature for Lipreading
Incremental Difference as Feature for Lipreading
 
Adpositional Argumentation: How Logic Originates In Natural Argumentative Dis...
Adpositional Argumentation: How Logic Originates In Natural Argumentative Dis...Adpositional Argumentation: How Logic Originates In Natural Argumentative Dis...
Adpositional Argumentation: How Logic Originates In Natural Argumentative Dis...
 
Slides: A glance at information-geometric signal processing
Slides: A glance at information-geometric signal processingSlides: A glance at information-geometric signal processing
Slides: A glance at information-geometric signal processing
 
Techfest jan17
Techfest jan17Techfest jan17
Techfest jan17
 
How do you know what I mean?: Psycholinguistics of spoken language communicat...
How do you know what I mean?: Psycholinguistics of spoken language communicat...How do you know what I mean?: Psycholinguistics of spoken language communicat...
How do you know what I mean?: Psycholinguistics of spoken language communicat...
 
Esa act
Esa actEsa act
Esa act
 
ESR11 Hoang Cuong - EXPERT Summer School - Malaga 2015
ESR11 Hoang Cuong - EXPERT Summer School - Malaga 2015ESR11 Hoang Cuong - EXPERT Summer School - Malaga 2015
ESR11 Hoang Cuong - EXPERT Summer School - Malaga 2015
 
Topic model an introduction
Topic model an introductionTopic model an introduction
Topic model an introduction
 
Allerton
AllertonAllerton
Allerton
 
Unit 6: All
Unit 6: AllUnit 6: All
Unit 6: All
 
Writing the discussion chapter for quantitative research.pdf
Writing the discussion chapter for quantitative research.pdfWriting the discussion chapter for quantitative research.pdf
Writing the discussion chapter for quantitative research.pdf
 
Speech To Sign Language Interpreter System
Speech To Sign Language Interpreter SystemSpeech To Sign Language Interpreter System
Speech To Sign Language Interpreter System
 

Plus de X 37

20200510 37
20200510 3720200510 37
20200510 37
X 37
 
20200322 inpainting
20200322 inpainting20200322 inpainting
20200322 inpainting
X 37
 
20200209 research note of "superhuman AI for multiplayer poker"
20200209 research note of "superhuman AI for multiplayer poker"20200209 research note of "superhuman AI for multiplayer poker"
20200209 research note of "superhuman AI for multiplayer poker"
X 37
 
20191027 bread house seminar
20191027 bread house seminar20191027 bread house seminar
20191027 bread house seminar
X 37
 
20190818 Bread Seminar
20190818 Bread Seminar20190818 Bread Seminar
20190818 Bread Seminar
X 37
 
paper repo - pre training for model robustness and uncertainty
paper repo - pre training for model robustness and uncertaintypaper repo - pre training for model robustness and uncertainty
paper repo - pre training for model robustness and uncertainty
X 37
 
Anomaly detection and change detection - sparse structure analysis -
Anomaly detection and change detection - sparse structure analysis -Anomaly detection and change detection - sparse structure analysis -
Anomaly detection and change detection - sparse structure analysis -
X 37
 
Reading papers - survey on Non-Convex Optimization
Reading papers - survey on Non-Convex OptimizationReading papers - survey on Non-Convex Optimization
Reading papers - survey on Non-Convex Optimization
X 37
 
20180520 MLPHS
20180520 MLPHS20180520 MLPHS
20180520 MLPHS
X 37
 

Plus de X 37 (9)

20200510 37
20200510 3720200510 37
20200510 37
 
20200322 inpainting
20200322 inpainting20200322 inpainting
20200322 inpainting
 
20200209 research note of "superhuman AI for multiplayer poker"
20200209 research note of "superhuman AI for multiplayer poker"20200209 research note of "superhuman AI for multiplayer poker"
20200209 research note of "superhuman AI for multiplayer poker"
 
20191027 bread house seminar
20191027 bread house seminar20191027 bread house seminar
20191027 bread house seminar
 
20190818 Bread Seminar
20190818 Bread Seminar20190818 Bread Seminar
20190818 Bread Seminar
 
paper repo - pre training for model robustness and uncertainty
paper repo - pre training for model robustness and uncertaintypaper repo - pre training for model robustness and uncertainty
paper repo - pre training for model robustness and uncertainty
 
Anomaly detection and change detection - sparse structure analysis -
Anomaly detection and change detection - sparse structure analysis -Anomaly detection and change detection - sparse structure analysis -
Anomaly detection and change detection - sparse structure analysis -
 
Reading papers - survey on Non-Convex Optimization
Reading papers - survey on Non-Convex OptimizationReading papers - survey on Non-Convex Optimization
Reading papers - survey on Non-Convex Optimization
 
20180520 MLPHS
20180520 MLPHS20180520 MLPHS
20180520 MLPHS
 

Dernier

Microbiology of Central Nervous System INFECTIONS.pdf
Microbiology of Central Nervous System INFECTIONS.pdfMicrobiology of Central Nervous System INFECTIONS.pdf
Microbiology of Central Nervous System INFECTIONS.pdf
sammy700571
 
Sciences of Europe journal No 142 (2024)
Sciences of Europe journal No 142 (2024)Sciences of Europe journal No 142 (2024)
Sciences of Europe journal No 142 (2024)
Sciences of Europe
 
Gadgets for management of stored product pests_Dr.UPR.pdf
Gadgets for management of stored product pests_Dr.UPR.pdfGadgets for management of stored product pests_Dr.UPR.pdf
Gadgets for management of stored product pests_Dr.UPR.pdf
PirithiRaju
 
fermented food science of sauerkraut.pptx
fermented food science of sauerkraut.pptxfermented food science of sauerkraut.pptx
fermented food science of sauerkraut.pptx
ananya23nair
 
Describing and Interpreting an Immersive Learning Case with the Immersion Cub...
Describing and Interpreting an Immersive Learning Case with the Immersion Cub...Describing and Interpreting an Immersive Learning Case with the Immersion Cub...
Describing and Interpreting an Immersive Learning Case with the Immersion Cub...
Leonel Morgado
 
Compexometric titration/Chelatorphy titration/chelating titration
Compexometric titration/Chelatorphy titration/chelating titrationCompexometric titration/Chelatorphy titration/chelating titration
Compexometric titration/Chelatorphy titration/chelating titration
Vandana Devesh Sharma
 
Sexuality - Issues, Attitude and Behaviour - Applied Social Psychology - Psyc...
Sexuality - Issues, Attitude and Behaviour - Applied Social Psychology - Psyc...Sexuality - Issues, Attitude and Behaviour - Applied Social Psychology - Psyc...
Sexuality - Issues, Attitude and Behaviour - Applied Social Psychology - Psyc...
PsychoTech Services
 
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
Advanced-Concepts-Team
 
CLASS 12th CHEMISTRY SOLID STATE ppt (Animated)
CLASS 12th CHEMISTRY SOLID STATE ppt (Animated)CLASS 12th CHEMISTRY SOLID STATE ppt (Animated)
CLASS 12th CHEMISTRY SOLID STATE ppt (Animated)
eitps1506
 
Candidate young stellar objects in the S-cluster: Kinematic analysis of a sub...
Candidate young stellar objects in the S-cluster: Kinematic analysis of a sub...Candidate young stellar objects in the S-cluster: Kinematic analysis of a sub...
Candidate young stellar objects in the S-cluster: Kinematic analysis of a sub...
Sérgio Sacani
 
Discovery of An Apparent Red, High-Velocity Type Ia Supernova at 𝐳 = 2.9 wi...
Discovery of An Apparent Red, High-Velocity Type Ia Supernova at  𝐳 = 2.9  wi...Discovery of An Apparent Red, High-Velocity Type Ia Supernova at  𝐳 = 2.9  wi...
Discovery of An Apparent Red, High-Velocity Type Ia Supernova at 𝐳 = 2.9 wi...
Sérgio Sacani
 
Pests of Storage_Identification_Dr.UPR.pdf
Pests of Storage_Identification_Dr.UPR.pdfPests of Storage_Identification_Dr.UPR.pdf
Pests of Storage_Identification_Dr.UPR.pdf
PirithiRaju
 
Juaristi, Jon. - El canon espanol. El legado de la cultura española a la civi...
Juaristi, Jon. - El canon espanol. El legado de la cultura española a la civi...Juaristi, Jon. - El canon espanol. El legado de la cultura española a la civi...
Juaristi, Jon. - El canon espanol. El legado de la cultura española a la civi...
frank0071
 
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
Sérgio Sacani
 
The cost of acquiring information by natural selection
The cost of acquiring information by natural selectionThe cost of acquiring information by natural selection
The cost of acquiring information by natural selection
Carl Bergstrom
 
23PH301 - Optics - Optical Lenses.pptx
23PH301 - Optics  -  Optical Lenses.pptx23PH301 - Optics  -  Optical Lenses.pptx
23PH301 - Optics - Optical Lenses.pptx
RDhivya6
 
Alternate Wetting and Drying - Climate Smart Agriculture
Alternate Wetting and Drying - Climate Smart AgricultureAlternate Wetting and Drying - Climate Smart Agriculture
Alternate Wetting and Drying - Climate Smart Agriculture
International Food Policy Research Institute- South Asia Office
 
Authoring a personal GPT for your research and practice: How we created the Q...
Authoring a personal GPT for your research and practice: How we created the Q...Authoring a personal GPT for your research and practice: How we created the Q...
Authoring a personal GPT for your research and practice: How we created the Q...
Leonel Morgado
 
11.1 Role of physical biological in deterioration of grains.pdf
11.1 Role of physical biological in deterioration of grains.pdf11.1 Role of physical biological in deterioration of grains.pdf
11.1 Role of physical biological in deterioration of grains.pdf
PirithiRaju
 
Tissue fluids_etiology_volume regulation_pressure.pptx
Tissue fluids_etiology_volume regulation_pressure.pptxTissue fluids_etiology_volume regulation_pressure.pptx
Tissue fluids_etiology_volume regulation_pressure.pptx
muralinath2
 

Dernier (20)

Microbiology of Central Nervous System INFECTIONS.pdf
Microbiology of Central Nervous System INFECTIONS.pdfMicrobiology of Central Nervous System INFECTIONS.pdf
Microbiology of Central Nervous System INFECTIONS.pdf
 
Sciences of Europe journal No 142 (2024)
Sciences of Europe journal No 142 (2024)Sciences of Europe journal No 142 (2024)
Sciences of Europe journal No 142 (2024)
 
Gadgets for management of stored product pests_Dr.UPR.pdf
Gadgets for management of stored product pests_Dr.UPR.pdfGadgets for management of stored product pests_Dr.UPR.pdf
Gadgets for management of stored product pests_Dr.UPR.pdf
 
fermented food science of sauerkraut.pptx
fermented food science of sauerkraut.pptxfermented food science of sauerkraut.pptx
fermented food science of sauerkraut.pptx
 
Describing and Interpreting an Immersive Learning Case with the Immersion Cub...
Describing and Interpreting an Immersive Learning Case with the Immersion Cub...Describing and Interpreting an Immersive Learning Case with the Immersion Cub...
Describing and Interpreting an Immersive Learning Case with the Immersion Cub...
 
Compexometric titration/Chelatorphy titration/chelating titration
Compexometric titration/Chelatorphy titration/chelating titrationCompexometric titration/Chelatorphy titration/chelating titration
Compexometric titration/Chelatorphy titration/chelating titration
 
Sexuality - Issues, Attitude and Behaviour - Applied Social Psychology - Psyc...
Sexuality - Issues, Attitude and Behaviour - Applied Social Psychology - Psyc...Sexuality - Issues, Attitude and Behaviour - Applied Social Psychology - Psyc...
Sexuality - Issues, Attitude and Behaviour - Applied Social Psychology - Psyc...
 
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
 
CLASS 12th CHEMISTRY SOLID STATE ppt (Animated)
CLASS 12th CHEMISTRY SOLID STATE ppt (Animated)CLASS 12th CHEMISTRY SOLID STATE ppt (Animated)
CLASS 12th CHEMISTRY SOLID STATE ppt (Animated)
 
Candidate young stellar objects in the S-cluster: Kinematic analysis of a sub...
Candidate young stellar objects in the S-cluster: Kinematic analysis of a sub...Candidate young stellar objects in the S-cluster: Kinematic analysis of a sub...
Candidate young stellar objects in the S-cluster: Kinematic analysis of a sub...
 
Discovery of An Apparent Red, High-Velocity Type Ia Supernova at 𝐳 = 2.9 wi...
Discovery of An Apparent Red, High-Velocity Type Ia Supernova at  𝐳 = 2.9  wi...Discovery of An Apparent Red, High-Velocity Type Ia Supernova at  𝐳 = 2.9  wi...
Discovery of An Apparent Red, High-Velocity Type Ia Supernova at 𝐳 = 2.9 wi...
 
Pests of Storage_Identification_Dr.UPR.pdf
Pests of Storage_Identification_Dr.UPR.pdfPests of Storage_Identification_Dr.UPR.pdf
Pests of Storage_Identification_Dr.UPR.pdf
 
Juaristi, Jon. - El canon espanol. El legado de la cultura española a la civi...
Juaristi, Jon. - El canon espanol. El legado de la cultura española a la civi...Juaristi, Jon. - El canon espanol. El legado de la cultura española a la civi...
Juaristi, Jon. - El canon espanol. El legado de la cultura española a la civi...
 
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
 
The cost of acquiring information by natural selection
The cost of acquiring information by natural selectionThe cost of acquiring information by natural selection
The cost of acquiring information by natural selection
 
23PH301 - Optics - Optical Lenses.pptx
23PH301 - Optics  -  Optical Lenses.pptx23PH301 - Optics  -  Optical Lenses.pptx
23PH301 - Optics - Optical Lenses.pptx
 
Alternate Wetting and Drying - Climate Smart Agriculture
Alternate Wetting and Drying - Climate Smart AgricultureAlternate Wetting and Drying - Climate Smart Agriculture
Alternate Wetting and Drying - Climate Smart Agriculture
 
Authoring a personal GPT for your research and practice: How we created the Q...
Authoring a personal GPT for your research and practice: How we created the Q...Authoring a personal GPT for your research and practice: How we created the Q...
Authoring a personal GPT for your research and practice: How we created the Q...
 
11.1 Role of physical biological in deterioration of grains.pdf
11.1 Role of physical biological in deterioration of grains.pdf11.1 Role of physical biological in deterioration of grains.pdf
11.1 Role of physical biological in deterioration of grains.pdf
 
Tissue fluids_etiology_volume regulation_pressure.pptx
Tissue fluids_etiology_volume regulation_pressure.pptxTissue fluids_etiology_volume regulation_pressure.pptx
Tissue fluids_etiology_volume regulation_pressure.pptx
 

20191215 rate distortion theory and VAEs

  • 1. BB UATOIN HOUSE SEMINAR ber, 2nd, 2017 aishu MINAMI Research of Rate-Distortion theory and Variational Auto-encoders Presentation: 37 (@_1_137) Date: Dec 15th, 2019 11:00~12:00 Place: Kernel Hongo
  • 2. Overview • Intro. of Rate-Distortion Theory - Elements of Information Theory, Thomas M. Cover, Joy A. Thomas (1991) • Bridge of Rate-Distortion theory and VAE - Fixing a Broken ELBO (Alemi+ ICML 2018) • Rate-Distortion theory and Memory distortion in humans (for coffee break) - An experimental study of the effect of language on the reproduction of visually perceived forms (Carmichael+ 1932) - Semantic Compression of Episodic Memories (Nagy+ 2018) • Recent research - Exact Rate-Distortion in Autoencoders via Echo Noise (Brekelmans+ NIPS 2019)
  • 3. Rate-Distortion Theory • This theory can state as follows: - Given a source distribution and a distortion measure, what is the minimum expected distortion achievable at a particular rate? - Or, what is the minimum rate required to achieve a particular distortion? R(D) = min p( ̂x|x):p(x)p( ̂x|x)d(x, ̂x)≤D I(X, ̂X) X → Y=f(X) → ̂XEncoder Decoder • Rate-Distortion theory: - created by Claude Shannon in 1948 in famous paper: “A Mathematical Theory of Communication” - We’d like to care about the mutual information MI(X, X’) and distortion D(X, X’) - Rate: the number of bits per data sample to be stored or transmitted - Distortion: the difference between input and output signal Elements of Informa.on Theory, Thomas M. Cover, Joy A. Thomas
  • 4. Examples of Rate Distortion curves a N(0, σ2) source with squared error distortion R(D) = { 1 2 log σ2 D , 0 ≤ D ≤ σ2 0 σ2 ≤ D Test channel ̂X ∼ N(0,σ2 − D) Z ∼ N(0,D) X ∼ N(0,σ2 ) a Bernoulli(p) source with Hamming distortion R(D) = { H(p) − H(D), 0 ≤ D ≤ min{p,1 − p} 0 D > min{p,1 − p} Test channel 1 − D 1 − D D D ̂X X 1 − p r p 1 − r Elements of Informa.on Theory, Thomas M. Cover, Joy A. Thomas
  • 5. Fixing a Broken ELBO Alexander A. Alemi, Ben Poole, Ian Fischer, Joshua V. Dillon, Rif A. Saurous, Kevin Murphy, ICML 2018 Alemi, A., Poole, B., Fischer, I., Dillon, J., Saurous, R., Murphy, K. (2017). Fixing a Broken ELBOhttps://arxiv.org/abs/1711.00464 β-VAE Loss function Testing RD-curve in several models (e,d,m): : simple or complex encoder : simple or complex decoder : simple, complex, or Vamp e ∈ { − , + } d ∈ { − , + } m ∈ { − , + ,v} Definition
  • 6. An experimental study of the effect of language on the reproduction of visually perceived forms • History: ✓ G. E. Müller, Zur Analyse der Gedächtnistätigkeit und des Vorstellungsverlaufes (1913) (For analysis of memory activity and the Mousse of ideas, translated by google) ✴ The reproduction changes after the passage of time ✓ F. Wulf, Über die Veränderung von Vorstellungen (Gedächtnis und Gestalt) in (1921) (changing ideas, translated by google) ✴ The identification involves the linguistic naming of the objects • Carmichael et al. reported the reproduction of visually perceived form by the use of language • Experiment: At first, the participants (60 subjects) received the stimulus figures with word list 1 or 2. assigned. Then, they reproduce the visual forms on each category. L. Carmichael, H. P. Hogan, A. A. Walter (1932) Carmichael, L., Hogan, H., Walter, A. (1932). An experimental study of the effect of language on the reproduction of visually perceived form. Journal of Experimental Psychology 15(1), 73. https:// dx.doi.org/10.1037/h0072671
  • 7. An experimental study of the effect of language on the reproduction of visually perceived forms • Result: Linguistic label distorts the memory and visual forms L. Carmichael, H. P. Hogan, A. A. Walter (1932) Carmichael, L., Hogan, H., Walter, A. (1932). An experimental study of the effect of language on the reproduction of visually perceived form. Journal of Experimental Psychology 15(1), 73. https:// dx.doi.org/10.1037/h0072671
  • 8. Semantic Compression of Episodic Memories • The relevance of RDT for explaining errors and biases in human visual working memory • Result below shows the reconstruction at different rates (changed value of β) David G. Nagy, Balazs Török, Gergõ Orbán (2018) Nagy, D., Török, B., Orbán, G. (2018). Semantic Compression of Episodic Memorieshttps://arxiv.org/abs/1806.07990
  • 9. • Idea: ✓ Let’s determine the noise in a data-driven fashion which doesn’t require restrictive prior distributional assumptions • Result: ✓ the model provided the exact expression for mutual information and outperformed flow- based method without the need to train additional distributional transformations • Losses: ✓ VAE Loss: ✓ Echo noise: • Echo noise properties: 1. z has the same distribution as 2. The mutual information is as follows: q(z|x) = μ(x) + σ(x)ϵ, ϵ ∼ N(0,I) q(z|x) = μ(x) + σ(x)ϵ(x), ϵ = ∞ ∑ l=0 (Πl l′=1σ(xl′ ))μ(xl ), xl ∼ q(x) ϵ I(X; Z) = − E log|detσ(x)| Exact Rate-Distortion in Autoencoders via Echo Noise Rob Brekelmans, Daniel Moyer, Aram Galstyan, Greg Ver Steeg, NIPS 2019 Brekelmans, R., Moyer, D., Galstyan, A., Steeg, G. (2019). Exact Rate-Distortion in Autoencoders via Echo Noisehttps://arxiv.org/abs/1904.07199 Illustration of setting μ(x) = x, σ(x) = 0.5
  • 10. • How do we derive the echo noise? ✓ We’d like to choose the noise to enforce an equivalence between the distributions q(z) and q(ε) for mutual information computation ✓ , ✓ Let’s make the noise match the channel output: ✓ ✓ We can guarantee that the noise and marginal distributions match in the limit • Lossy Compression in VAEs ✓ ELBO ✓ KL term • Rate-Distortion Objective q(z) = ∫ qϕ(z|x)q(x)dx qϕ(z|x) = μ(x) + σ(x)ϵ ϵ = μ(x′), x′ ∼ q(x) ϵ = μ(x0 ) + σ(x0 )(μ(x1 ) + σ(x1 )(μ(x2 ) + σ(x2 ) . . . Exact Rate-Distortion in Autoencoders via Echo Noise Rob Brekelmans, Daniel Moyer, Aram Galstyan, Greg Ver Steeg, NIPS 2019 Brekelmans, R., Moyer, D., Galstyan, A., Steeg, G. (2019). Exact Rate-Distortion in Autoencoders via Echo Noisehttps://arxiv.org/abs/1904.07199
  • 11. • At low rates, Echo maintain only high level features of the input image • At high rates, Echo gives the better reconstruction error than Info VA Exact Rate-Distortion in Autoencoders via Echo Noise Rob Brekelmans, Daniel Moyer, Aram Galstyan, Greg Ver Steeg, NIPS 2019 Brekelmans, R., Moyer, D., Galstyan, A., Steeg, G. (2019). Exact Rate-Distortion in Autoencoders via Echo Noisehttps://arxiv.org/abs/1904.07199