SlideShare a Scribd company logo
1 of 11
Download to read offline
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

More Related Content

What's hot

Hybrid Beamforming Projects Research Topics
Hybrid Beamforming Projects Research TopicsHybrid Beamforming Projects Research Topics
Hybrid Beamforming Projects Research TopicsMatlab Simulation
 
Digital Image Processing: Image Restoration
Digital Image Processing: Image RestorationDigital Image Processing: Image Restoration
Digital Image Processing: Image RestorationMostafa G. M. Mostafa
 
Optimization for Deep Learning
Optimization for Deep LearningOptimization for Deep Learning
Optimization for Deep LearningSebastian Ruder
 
Implementation of Vedic multipliers using urdhwa triyakbhyam sutra
Implementation of Vedic multipliers using urdhwa triyakbhyam sutraImplementation of Vedic multipliers using urdhwa triyakbhyam sutra
Implementation of Vedic multipliers using urdhwa triyakbhyam sutraGana Thennira
 
Digital Image Processing - Image Compression
Digital Image Processing - Image CompressionDigital Image Processing - Image Compression
Digital Image Processing - Image CompressionMathankumar S
 
markov chain.ppt
markov chain.pptmarkov chain.ppt
markov chain.pptDWin Myo
 
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...홍배 김
 
Kernels in convolution
Kernels in convolutionKernels in convolution
Kernels in convolutionRevanth Kumar
 
Image-to-Image Translation
Image-to-Image TranslationImage-to-Image Translation
Image-to-Image TranslationJunho Kim
 
Pixel Relationships Examples
Pixel Relationships ExamplesPixel Relationships Examples
Pixel Relationships ExamplesMarwa Ahmeid
 
Restricted Boltzman Machine (RBM) presentation of fundamental theory
Restricted Boltzman Machine (RBM) presentation of fundamental theoryRestricted Boltzman Machine (RBM) presentation of fundamental theory
Restricted Boltzman Machine (RBM) presentation of fundamental theorySeongwon Hwang
 
Enhanced Deep Residual Networks for Single Image Super-Resolution
Enhanced Deep Residual Networks for Single Image Super-ResolutionEnhanced Deep Residual Networks for Single Image Super-Resolution
Enhanced Deep Residual Networks for Single Image Super-ResolutionNAVER Engineering
 
"Using Deep Learning for Video Event Detection on a Compute Budget," a Presen...
"Using Deep Learning for Video Event Detection on a Compute Budget," a Presen..."Using Deep Learning for Video Event Detection on a Compute Budget," a Presen...
"Using Deep Learning for Video Event Detection on a Compute Budget," a Presen...Edge AI and Vision Alliance
 
Filtering an image is to apply a convolution
Filtering an image is to apply a convolutionFiltering an image is to apply a convolution
Filtering an image is to apply a convolutionAbhishek Mukherjee
 
Discrete fourier transform
Discrete fourier transformDiscrete fourier transform
Discrete fourier transformMOHAMMAD AKRAM
 
Discrete cosine transform
Discrete cosine transform   Discrete cosine transform
Discrete cosine transform Rashmi Karkra
 

What's hot (20)

Wasserstein GAN
Wasserstein GANWasserstein GAN
Wasserstein GAN
 
Edge detection
Edge detectionEdge detection
Edge detection
 
Hybrid Beamforming Projects Research Topics
Hybrid Beamforming Projects Research TopicsHybrid Beamforming Projects Research Topics
Hybrid Beamforming Projects Research Topics
 
Digital Image Processing: Image Restoration
Digital Image Processing: Image RestorationDigital Image Processing: Image Restoration
Digital Image Processing: Image Restoration
 
Optimization for Deep Learning
Optimization for Deep LearningOptimization for Deep Learning
Optimization for Deep Learning
 
Implementation of Vedic multipliers using urdhwa triyakbhyam sutra
Implementation of Vedic multipliers using urdhwa triyakbhyam sutraImplementation of Vedic multipliers using urdhwa triyakbhyam sutra
Implementation of Vedic multipliers using urdhwa triyakbhyam sutra
 
Digital Image Processing - Image Compression
Digital Image Processing - Image CompressionDigital Image Processing - Image Compression
Digital Image Processing - Image Compression
 
markov chain.ppt
markov chain.pptmarkov chain.ppt
markov chain.ppt
 
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
 
Kernels in convolution
Kernels in convolutionKernels in convolution
Kernels in convolution
 
Image-to-Image Translation
Image-to-Image TranslationImage-to-Image Translation
Image-to-Image Translation
 
Pixel Relationships Examples
Pixel Relationships ExamplesPixel Relationships Examples
Pixel Relationships Examples
 
Restricted Boltzman Machine (RBM) presentation of fundamental theory
Restricted Boltzman Machine (RBM) presentation of fundamental theoryRestricted Boltzman Machine (RBM) presentation of fundamental theory
Restricted Boltzman Machine (RBM) presentation of fundamental theory
 
Enhanced Deep Residual Networks for Single Image Super-Resolution
Enhanced Deep Residual Networks for Single Image Super-ResolutionEnhanced Deep Residual Networks for Single Image Super-Resolution
Enhanced Deep Residual Networks for Single Image Super-Resolution
 
"Using Deep Learning for Video Event Detection on a Compute Budget," a Presen...
"Using Deep Learning for Video Event Detection on a Compute Budget," a Presen..."Using Deep Learning for Video Event Detection on a Compute Budget," a Presen...
"Using Deep Learning for Video Event Detection on a Compute Budget," a Presen...
 
Huffman Coding
Huffman CodingHuffman Coding
Huffman Coding
 
CSC446: Pattern Recognition (LN6)
CSC446: Pattern Recognition (LN6)CSC446: Pattern Recognition (LN6)
CSC446: Pattern Recognition (LN6)
 
Filtering an image is to apply a convolution
Filtering an image is to apply a convolutionFiltering an image is to apply a convolution
Filtering an image is to apply a convolution
 
Discrete fourier transform
Discrete fourier transformDiscrete fourier transform
Discrete fourier transform
 
Discrete cosine transform
Discrete cosine transform   Discrete cosine transform
Discrete cosine transform
 

Similar to 20191215 rate distortion theory and VAEs

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 environmentOHSU | Oregon Health & Science University
 
129966864160453838[1]
129966864160453838[1]129966864160453838[1]
129966864160453838[1]威華 王
 
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
 
Incremental Difference as Feature for Lipreading
Incremental Difference as Feature for LipreadingIncremental Difference as Feature for Lipreading
Incremental Difference as Feature for LipreadingIDES 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 processingFrank Nielsen
 
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
 
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 2015RIILP
 
Topic model an introduction
Topic model an introductionTopic model an introduction
Topic model an introductionYueshen Xu
 
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.pdfMartin McMorrow
 
Speech To Sign Language Interpreter System
Speech To Sign Language Interpreter SystemSpeech To Sign Language Interpreter System
Speech To Sign Language Interpreter Systemkkkseld
 

Similar to 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
 

More from X 37

20200510 37
20200510 3720200510 37
20200510 37X 37
 
20200322 inpainting
20200322 inpainting20200322 inpainting
20200322 inpaintingX 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 seminarX 37
 
20190818 Bread Seminar
20190818 Bread Seminar20190818 Bread Seminar
20190818 Bread SeminarX 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 uncertaintyX 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 OptimizationX 37
 
20180520 MLPHS
20180520 MLPHS20180520 MLPHS
20180520 MLPHSX 37
 

More from 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
 

Recently uploaded

Cyathodium bryophyte: morphology, anatomy, reproduction etc.
Cyathodium bryophyte: morphology, anatomy, reproduction etc.Cyathodium bryophyte: morphology, anatomy, reproduction etc.
Cyathodium bryophyte: morphology, anatomy, reproduction etc.Cherry
 
X-rays from a Central “Exhaust Vent” of the Galactic Center Chimney
X-rays from a Central “Exhaust Vent” of the Galactic Center ChimneyX-rays from a Central “Exhaust Vent” of the Galactic Center Chimney
X-rays from a Central “Exhaust Vent” of the Galactic Center ChimneySérgio Sacani
 
POGONATUM : morphology, anatomy, reproduction etc.
POGONATUM : morphology, anatomy, reproduction etc.POGONATUM : morphology, anatomy, reproduction etc.
POGONATUM : morphology, anatomy, reproduction etc.Cherry
 
Dr. E. Muralinath_ Blood indices_clinical aspects
Dr. E. Muralinath_ Blood indices_clinical  aspectsDr. E. Muralinath_ Blood indices_clinical  aspects
Dr. E. Muralinath_ Blood indices_clinical aspectsmuralinath2
 
Use of mutants in understanding seedling development.pptx
Use of mutants in understanding seedling development.pptxUse of mutants in understanding seedling development.pptx
Use of mutants in understanding seedling development.pptxRenuJangid3
 
CYTOGENETIC MAP................ ppt.pptx
CYTOGENETIC MAP................ ppt.pptxCYTOGENETIC MAP................ ppt.pptx
CYTOGENETIC MAP................ ppt.pptxCherry
 
Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....
Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....
Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....muralinath2
 
development of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusdevelopment of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusNazaninKarimi6
 
Factory Acceptance Test( FAT).pptx .
Factory Acceptance Test( FAT).pptx       .Factory Acceptance Test( FAT).pptx       .
Factory Acceptance Test( FAT).pptx .Poonam Aher Patil
 
Climate Change Impacts on Terrestrial and Aquatic Ecosystems.pptx
Climate Change Impacts on Terrestrial and Aquatic Ecosystems.pptxClimate Change Impacts on Terrestrial and Aquatic Ecosystems.pptx
Climate Change Impacts on Terrestrial and Aquatic Ecosystems.pptxDiariAli
 
Understanding Partial Differential Equations: Types and Solution Methods
Understanding Partial Differential Equations: Types and Solution MethodsUnderstanding Partial Differential Equations: Types and Solution Methods
Understanding Partial Differential Equations: Types and Solution Methodsimroshankoirala
 
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...Scintica Instrumentation
 
GBSN - Microbiology (Unit 3)Defense Mechanism of the body
GBSN - Microbiology (Unit 3)Defense Mechanism of the body GBSN - Microbiology (Unit 3)Defense Mechanism of the body
GBSN - Microbiology (Unit 3)Defense Mechanism of the body Areesha Ahmad
 
Module for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learningModule for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learninglevieagacer
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsSérgio Sacani
 
LUNULARIA -features, morphology, anatomy ,reproduction etc.
LUNULARIA -features, morphology, anatomy ,reproduction etc.LUNULARIA -features, morphology, anatomy ,reproduction etc.
LUNULARIA -features, morphology, anatomy ,reproduction etc.Cherry
 
PODOCARPUS...........................pptx
PODOCARPUS...........................pptxPODOCARPUS...........................pptx
PODOCARPUS...........................pptxCherry
 
Digital Dentistry.Digital Dentistryvv.pptx
Digital Dentistry.Digital Dentistryvv.pptxDigital Dentistry.Digital Dentistryvv.pptx
Digital Dentistry.Digital Dentistryvv.pptxMohamedFarag457087
 
Efficient spin-up of Earth System Models usingsequence acceleration
Efficient spin-up of Earth System Models usingsequence accelerationEfficient spin-up of Earth System Models usingsequence acceleration
Efficient spin-up of Earth System Models usingsequence accelerationSérgio Sacani
 
The Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptxThe Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptxseri bangash
 

Recently uploaded (20)

Cyathodium bryophyte: morphology, anatomy, reproduction etc.
Cyathodium bryophyte: morphology, anatomy, reproduction etc.Cyathodium bryophyte: morphology, anatomy, reproduction etc.
Cyathodium bryophyte: morphology, anatomy, reproduction etc.
 
X-rays from a Central “Exhaust Vent” of the Galactic Center Chimney
X-rays from a Central “Exhaust Vent” of the Galactic Center ChimneyX-rays from a Central “Exhaust Vent” of the Galactic Center Chimney
X-rays from a Central “Exhaust Vent” of the Galactic Center Chimney
 
POGONATUM : morphology, anatomy, reproduction etc.
POGONATUM : morphology, anatomy, reproduction etc.POGONATUM : morphology, anatomy, reproduction etc.
POGONATUM : morphology, anatomy, reproduction etc.
 
Dr. E. Muralinath_ Blood indices_clinical aspects
Dr. E. Muralinath_ Blood indices_clinical  aspectsDr. E. Muralinath_ Blood indices_clinical  aspects
Dr. E. Muralinath_ Blood indices_clinical aspects
 
Use of mutants in understanding seedling development.pptx
Use of mutants in understanding seedling development.pptxUse of mutants in understanding seedling development.pptx
Use of mutants in understanding seedling development.pptx
 
CYTOGENETIC MAP................ ppt.pptx
CYTOGENETIC MAP................ ppt.pptxCYTOGENETIC MAP................ ppt.pptx
CYTOGENETIC MAP................ ppt.pptx
 
Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....
Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....
Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....
 
development of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusdevelopment of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virus
 
Factory Acceptance Test( FAT).pptx .
Factory Acceptance Test( FAT).pptx       .Factory Acceptance Test( FAT).pptx       .
Factory Acceptance Test( FAT).pptx .
 
Climate Change Impacts on Terrestrial and Aquatic Ecosystems.pptx
Climate Change Impacts on Terrestrial and Aquatic Ecosystems.pptxClimate Change Impacts on Terrestrial and Aquatic Ecosystems.pptx
Climate Change Impacts on Terrestrial and Aquatic Ecosystems.pptx
 
Understanding Partial Differential Equations: Types and Solution Methods
Understanding Partial Differential Equations: Types and Solution MethodsUnderstanding Partial Differential Equations: Types and Solution Methods
Understanding Partial Differential Equations: Types and Solution Methods
 
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
 
GBSN - Microbiology (Unit 3)Defense Mechanism of the body
GBSN - Microbiology (Unit 3)Defense Mechanism of the body GBSN - Microbiology (Unit 3)Defense Mechanism of the body
GBSN - Microbiology (Unit 3)Defense Mechanism of the body
 
Module for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learningModule for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learning
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
 
LUNULARIA -features, morphology, anatomy ,reproduction etc.
LUNULARIA -features, morphology, anatomy ,reproduction etc.LUNULARIA -features, morphology, anatomy ,reproduction etc.
LUNULARIA -features, morphology, anatomy ,reproduction etc.
 
PODOCARPUS...........................pptx
PODOCARPUS...........................pptxPODOCARPUS...........................pptx
PODOCARPUS...........................pptx
 
Digital Dentistry.Digital Dentistryvv.pptx
Digital Dentistry.Digital Dentistryvv.pptxDigital Dentistry.Digital Dentistryvv.pptx
Digital Dentistry.Digital Dentistryvv.pptx
 
Efficient spin-up of Earth System Models usingsequence acceleration
Efficient spin-up of Earth System Models usingsequence accelerationEfficient spin-up of Earth System Models usingsequence acceleration
Efficient spin-up of Earth System Models usingsequence acceleration
 
The Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptxThe Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.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