Sparse Modeling of Data and its Relation to
- Slides: 59
Sparse Modeling of Data and its Relation to Deep Learning Michael Elad Computer Science Department The Technion - Israel Institute of Technology Haifa 32000, Israel
This Lecture is About … A Proposed Theory for Deep-Learning (DL) Explanation: o DL has been extremely successful in solving a variety of learning problems o DL is an empirical field, with numerous tricks and know-how, but almost no theoretical foundations o A theory for DL has become the holy-grail of current research in Machine-Learning and related fields Michael Elad The Computer-Science Department The Technion 2
Who Needs Theory ? We All Do !! … because … A theory o … could bring the next rounds of ideas to this field, breaking existing barriers and opening new opportunities o … could map clearly the limitations of existing DL solutions, and point to key features that control their performance o … could remove the feeling with many of us that DL is a “dark magic”, turning it into a solid scientific discipline Michael Elad The Computer-Science Department The Technion Ali Rahimi: NIPS 2017 Test -of-Time Award “Machine learning has become alchemy” Yan Le. Cun Understanding is a good thing … but another goal is inventing methods. In the history of science and technology, engineering preceded theoretical understanding: § Lens & telescope Optics § Steam engine Thermodynamics § Airplane Aerodynamics § Radio & Comm. Info. Theory § Computer Science 3
A Theory for DL ? Raja Giryes (TAU): Studied the architecture of DNN in the context of their ability to give distance-preserving embedding of signals Stephane Mallat (ENS) & Joan Bruna (NYU): Proposed the scattering transform (wavelet-based) and emphasized the treatment of invariances in the input data Richard Baraniuk & Ankit Patel (RICE): Offered a generative probabilistic model for the data, showing how classic architectures and learning algorithms relate to it Gitta Kutyniok (TU) & Helmut Bolcskei (ETH): Studied the ability of DNN architectures to approximate families of functions Architecture Data Algorithms Rene Vidal (JHU): Explained the ability to optimize the typical nonconvex objective and yet get to a global minima Naftali Tishby (HUJI): Introduced the Information Bottleneck (IB) concept and demonstrated its relevance to deep learning Stefano Soatto’s team (UCLA): Analyzed the Stochastic Gradient Descent (SGD) algorithm, connecting it to the IB objective Michael Elad The Computer-Science Department The Technion 4
So, is there a Theory for DL ? The answer is tricky: There already various such attempts, and some of them are truly impressive … but … The complete picture is far from complete Michael Elad The Computer-Science Department The Technion 5
Interesting Observations o Theory origins: Signal Proc. , Control Theory, Info. Theory, Harmonic Analysis, Sparse Represen. , Quantum Physics, PDE, Machine learning … Ron Kimmel: “DL is a dark monster covered with mirrors. Everyone sees his reflection in it …” David Donoho: “… these mirrors are taken from Cinderella's story, telling each that he is the most beautiful” o Today’s talk is on our proposed theory: Architecture Data Algorithms Yaniv Romano Vardan Papyan Jeremias Sulam Aviad Aberdam Michael Elad The Computer-Science Department The Technion … and our theory is the best 6
This Lecture: More Specifically Sparseland Sparse Representation Theory CSC Convolutional Sparse Coding Sparsity-Inspired Models Another underlying idea that accompanies us Generative modeling of data sources enables o A systematic algorithm development, & o A theoretical analysis of their performance Michael Elad The Computer-Science Department The Technion ML-CSC Multi -Layered Convolutional Sparse Coding Deep-Learning Being a lecture on theory of DL, this lecture is … theoretical … and mathematically oriented 7
Our eventual goal in today’s talk is to present the … Multi-Layered Convolutional Sparse Modeling So, lets use this as our running title, parse it into words, and explain each of them Michael Elad The Computer-Science Department The Technion 8
Multi-Layered Convolutional Sparse Modeling Michael Elad The Computer-Science Department The Technion 9
Our Data is Structured Stock Market Text Documents Matrix Data Biological Signals Still Images Social Networks Videos Seismic Data Using models Radar Imaging o We are surrounded by various diverse sources of massive information o Each of these sources have an internal structure, which can be exploited o This structure, when identified, is the engine behind the ability to process data o How to identify structure? Michael Elad The Computer-Science Department The Technion Traffic info Voice Signals 3 D Objects Medical Imaging 10
Models o A model: a mathematical description of the underlying signal of interest, describing our beliefs regarding its structure o The following is a partial list of commonly used models for images o Good models should be simple while matching the signals Simplicity Reliability o Models are almost always imperfect Michael Elad The Computer-Science Department The Technion Principal-Component-Analysis Gaussian-Mixture Markov Random Field Laplacian Smoothness DCT concentration Wavelet Sparsity Piece-Wise-Smoothness C 2 -smoothness Besov-Spaces Total-Variation Beltrami-Flow 12
What this Talk is all About? Data Models and Their Use o Almost any task in data processing requires a model – true for denoising, deblurring, super-resolution, inpainting, compression, anomaly-detection, sampling, recognition, separation, and more o Sparse and Redundant Representations offer a new and highly effective model – we call it Sparseland o We shall describe this and descendant versions of it that lead all the way to … deep-learning Michael Elad The Computer-Science Department The Technion 13
Multi-Layered Convolutional Sparse Modeling Michael Elad The Computer-Science Department The Technion 14
A New Emerging Model Machine Learning Signal Processing Mathematics Approximation Theory Wavelet Theory Multi-Scale Analysis Sparsela nd Signal Transforms Semi-Supervised Learning Compression Linear Algebra Interpolation Inference (solving inverse problems) Recognition Michael Elad The Computer-Science Department The Technion Source. Separation Prediction Clustering Optimization Theory Segmentation Sensor-Fusion Classification Summarizing Denoising Anomaly Identification detection Synthesis 15
The Sparseland Model o Task: model image patches of size 8× 8 pixels o We assume that a dictionary of such image patches is given, containing 256 atom images Σ α 1 α 2 α 3 o The Sparseland model assumption: every image patch can be described as a linear combination of few atoms Michael Elad The Computer-Science Department The Technion 16
The Sparseland Model Properties of this model: Σ Sparsity and Redundancy o We start with a 8 -by-8 pixels patch and represent it using 256 numbers – This is a redundant representation α 1 α 2 α 3 o However, out of those 256 elements in the representation, only 3 are non-zeros – This is a sparse representation o Bottom line in this case: 64 numbers representing the patch are replaced by 6 (3 for the indices of the non-zeros, and 3 for their entries) Michael Elad The Computer-Science Department The Technion 17
Chemistry of Data We could refer to the Sparseland model as the chemistry of information: o Our dictionary stands for the Periodic Table containing all the elements Σ α 1 α 2 α 3 o Our model follows a similar rationale: Every molecule is built of few elements Michael Elad The Computer-Science Department The Technion 18
Sparseland : A Formal Description m M n A Dictionary A sparse vector o The vector is generated n with few nonzeros at arbitrary locations and values o This is a generative model that describes how (we believe) signals are created Michael Elad The Computer-Science Department The Technion 19
Difficulties with Sparseland o Problem 1: Given a signal, how can we find its atom decomposition? o A simple example: Σ α 1 α 2 α 3 § There are 2000 atoms in the dictionary § The signal is known to be built of 15 atoms possibilities § If each of these takes 1 nano-sec to test, will take ~7. 5 e 20 years to finish !!!!!! this o So, are we stuck? Michael Elad The Computer-Science Department The Technion 20
Atom Decomposition Made Formal n m Approximation Algorithms § L 0 – counting number of non-zeros in the vector Relaxation methods Greedy methods Basis-Pursuit Thresholding/OMP Michael Elad The Computer-Science Department The Technion § This is a projection onto the Sparseland model § These problems are known to be NP-Hard problem 21
Pursuit Algorithms Approximation Algorithms Basis Pursuit Change the L 0 into L 1 and then the problem becomes convex and manageable Michael Elad The Computer-Science Department The Technion 22
Difficulties with Sparseland o There are various pursuit algorithms o Here is an example using the Basis Pursuit (L 1): Σ α 1 α 2 α 3 o Surprising fact: Many of these algorithms are often accompanied by theoretical guarantees for their success, if the unknown is sparse enough Michael Elad The Computer-Science Department The Technion 23
The Mutual Coherence o Compute = Assume normalized columns Michael Elad The Computer-Science Department The Technion 24
Basis-Pursuit Success Donoho, Elad & Temlyakov (‘ 06) + M Michael Elad The Computer-Science Department The Technion 25
Difficulties with Sparseland o Problem 2: Given a family of signals, how do we find the dictionary to represent it well? o Solution: Learn! Gather a large set of signals (many thousands), and find the dictionary that sparsifies them Σ α 1 α 2 α 3 o Such algorithms were developed in the past 10 years (e. g. , K-SVD), and their performance is surprisingly good o We will not discuss this matter further in this talk due to lack of time Michael Elad The Computer-Science Department The Technion 26
Difficulties with Sparseland o Problem 3: Why is this model suitable to describe various sources? e. g. , Is it good for images? Audio? Stocks? … o General answer: Yes, this model is extremely effective in representing various sources Σ α 1 α 2 α 3 § Theoretical answer: Clear connection to other models § Empirical answer: In a large variety of signal and image processing (and later machine learning), this model has been shown to lead to state-of-the-art results Michael Elad The Computer-Science Department The Technion 27
Difficulties with Sparseland o Problem 1: Given an image patch, how can we find its atom decomposition ? o o D E Problem 2: Given a family of signals, R E Wdictionary Sthe D how do we A find to N N A L Y L L represent A it well? E Y L V I E T V I I S T O C Problem model flexible P 3: Is this U R T various sources? S enough to describe N O C E. g. , Is it good for images? audio? … Michael Elad The Computer-Science Department The Technion ? Σ α 1 α 2 α 3 28
This Field has been rapidly GROWI NG … o Sparseland has a great success in signal & image processing & machine learning o In the past 8 -9 years, many books were published on this and closely related fields Michael Elad The Computer-Science Department The Technion 29
Sparseland for Image Processing o When handling images, Sparseland is typically deployed on small overlapping patches due to the desire to train the model to fit the data better o The model assumption is: each patch in the image is believed to have a sparse representation w. r. t. a common local dictionary o What is the corresponding global model? This brings us to … the Convolutional Sparse Coding (CSC) Michael Elad The Computer-Science Department The Technion 30
Multi-Layered Convolutional Sparse Modeling Joint work with 1. V. Papyan, J. Sulam, and M. Elad, Working Locally Thinking Globally: Theoretical Guarantees for Convolutional Sparse Coding, IEEE Trans. on Signal Processing, Vol. 65, No. 21, Pages 5687 -5701, November 2017. Michael Elad The Computer-Science Department The Technion Yaniv Romano Vardan Papyan Jeremias Sulam 31
Convolutional Sparse Coding (CSC) This model emerged in 2005 -2010, developed and advocated by Yan Le. Cun and others. It serves as the foundation of Convolutional Neural Networks Michael Elad The Computer-Science Department The Technion 32
CSC in Matrix Form • Michael Elad The Computer-Science Department The Technion 33
The CSC Dictionary Michael Elad The Computer-Science Department The Technion 34
Why CSC? = Ω stripe-dictionary Michael Elad The Computer-Science Department The Technion stripe vector 36
Classical Sparse Theory for CSC ? • ory e h T d n a l e s r ns a o p i t S a c n i s a l s p ex d o The cla o g e vid o r p l t e o d n o m C does S for the C Michael Elad The Computer-Science Department The Technion 35
Moving to Local Sparsity: Stripes The main question we aim to address is this: Can we generalize the vast theory of Sparseland to this new notion of local sparsity? For example, could we provide guarantees for success for pursuit algorithms? Michael Elad The Computer-Science Department The Technion 37
Success of the Basis Pursuit Papyan, Sulam & Elad (‘ 17) Michael Elad The Computer-Science Department The Technion 38
Multi-Layered Convolutional Sparse Modeling Yaniv Romano Vardan Papyan Jeremias Sulam Michael Elad The Computer-Science Department The Technion 2. V. Papyan, Y. Romano, and M. Elad, Convolutional Neural Networks Analyzed via Convolutional Sparse Coding, Journal of Machine Learning Research, Vol. 18, Pages 1 -52, July 2017. 3. V. Papyan, Y. Romano, J. Sulam, and M. Elad, Theoretical Foundations of Deep Learning via Sparse Representations, IEEE Signal Processing Magazine, Vol. 35, No. 4, Pages 72 -89, June 2018. 39
From CSC to Multi-Layered CSC We propose to impose the same structure on the representations themselves Convolutional sparsity (CSC) assumes an inherent structure is present in natural signals Multi-Layer CSC (ML-CSC) Michael Elad The Computer-Science Department The Technion 40
Intuition: From Atoms to Molecules & atoms molecules cells tissue body-parts … Michael Elad The Computer-Science Department The Technion 41
Intuition: From Atoms to Molecules Michael Elad The Computer-Science Department The Technion 42
A Small Taste: Model Training (MNIST) MNIST Dictionary: • D 1: 32 filters of size 7× 7, with stride of 2 (dense) • D 2: 128 filters of size 5× 5× 32 with stride of 1 - 99. 09 % sparse • D 3: 1024 filters of size 7× 7× 128 – 99. 89 % sparse Michael Elad The Computer-Science Department The Technion 43
ML-CSC: Pursuit Michael Elad The Computer-Science Department The Technion 44
A Small Taste: Pursuit x 94. 51 % sparse (213 nnz) 99. 52% sparse (30 nnz) 99. 51% sparse (5 nnz) Michael Elad The Computer-Science Department The Technion 45
ML-CSC: The Simplest Pursuit • Michael Elad The Computer-Science Department The Technion 46
Consider this for Solving the DCP o Layered Thresholding (LT): o Now let’s take a look at how Conv. Neural Network operates: The layered (soft nonnegative) thresholding and the CNN forward pass algorithm are the very same thing !!! Michael Elad The Computer-Science Department The Technion 47
Theoretical Path M A Armed with this view of a generative source model, we may ask new and daring theoretical questions Michael Elad The Computer-Science Department The Technion 48
Success of the Layered-THR Papyan, Romano & Elad (‘ 17) The stability of the forward pass is guaranteed if the underlying representations are locally sparse and the noise is locally bounded Michael Elad The Computer-Science Department The Technion Problems: 1. Contrast 2. Error growth 3. Error even if no noise 49
Layered Basis Pursuit (BP) o We chose the Thresholding algorithm due to its simplicity, but we do know that there are better pursuit methods – how about using them? o Lets use the Basis Pursuit instead … Deconvolutional networks [Zeiler, Krishnan, Taylor & Fergus ‘ 10] Michael Elad The Computer-Science Department The Technion 50
Success of the Layered BP Papyan, Romano & Elad (‘ 17) Michael Elad The Computer-Science Department The Technion Problems: 1. Contrast 2. Error growth 3. Error even if no noise 51
Layered Iterative Thresholding Note that our suggestion implies that groups of layers share the same dictionaries Michael Elad The Computer-Science Department The Technion Can be seen as a very deep residual neural network [He, Zhang, Ren, & Sun ‘ 15] 52
Where are the Labels? Answer 1: M o We do not need labels because everything we show refer to the unsupervised case, in which we operate on signals, not necessarily in the context of recognition We presented the ML-CSC as a machine that produces signals X Michael Elad The Computer-Science Department The Technion 54
Where are the Labels? M We presented the ML-CSC as a machine that produces signals X Michael Elad The Computer-Science Department The Technion 55
What About Learning? Sparseland Sparse Representation Theory CSC Convolutional Sparse Coding ML-CSC Multi -Layered Convolutional Sparse Coding All these models rely on proper Dictionary Learning Algorithms to fulfil their mission: § Sparseland: We have unsupervised and supervised such algorithms, and a beginning of theory to explain how these work § CSC: We have few and only unsupervised methods, and even these are not fully stable/clear § ML-CSC: Two algorithms were proposed – unsupervised and supervised Michael Elad The Computer-Science Department The Technion 56
Time to Conclude Michael Elad The Computer-Science Department The Technion 61
This Talk Take Home Message 1: Generative modeling of data sources enables algorithm development along with theoretically analyzing algorithms’ performance Sparsela nd The desire to model data Novel View of Convolutional Sparse Coding Take Home Message 2: The Multi-Layer Convolutional Sparse Multi-Layer A novel interpretation Coding model could be Convolutional and theoretical a new platform for Sparse Coding understanding of CNN understanding and We spoke The ML-CSC about was the shown importance toextension enable a models theoretical signal/image developing deeppropose a multi-layer of presented a theoretical studyofof the CSCin model and study ofoperate CNN, with new insights CSC, shown to along be tightly connected to CNN how to locally while getting global processing and described Sparseland in optimality details learning solutions Michael Elad The Computer-Science Department The Technion 62
On a Personal Note … Disclaimer: True, I am biased, so take what I say with a grain of salt … Conjecture: Sparse modeling of data is at the heart of the Deep-Learning ideas, and as such, it is the main avenue for developing theoretical foundations for this field. Elad (‘ 19) My research activity in the foreseen future will be dedicated to establishing this connection, addressing various aspects of it Michael Elad The Computer-Science Department The Technion 63
Fresh from the Oven My team’s work proceeds along the above-described line of thinking: 4. J. Sulam, V. Papyan, Y. Romano, and M. Elad, Multi-Layer Convolutional Sparse Modeling: Pursuit and Dictionary Learning, IEEE Trans. on Signal Proc. , Vol. 66, No. 15, Pages 4090 -4104, August 2018. 5. A. Aberdam, J. Sulam, and M. Elad, Multi Layer Sparse Coding: the Holistic Way, SIAM Journal on Mathematics of Data Science (SIMODS), Vol. 1, No. 1, Pages 46 -77. 6. J. Sulam, A. Aberdam, A. Beck, and M. Elad, On Multi-Layer Basis Pursuit, Efficient Algorithms and Convolutional Neural Networks, to appear in IEEE T-PAMI. 7. Y. Romano, A. Aberdam, J. Sulam, and M. Elad, Adversarial Noise Attacks of Deep Learning Architectures – Stability Analysis via Sparse Modeled Signals, to appear in JMIV. 8. Ev Zisselman, Jeremias Sulam, and Michael Elad, A Local Block Coordinate Descent Algorithm for the CSC Model, CVPR 2019. 9. I. Rey-Otero, J. Sulam, and M. Elad, Variations on the CSC model, to appear in IEEE Transactions on Signal Processing. 10. D. Simon and M. Elad, Rethinking the CSC model for Natural Images, NIPS 2019. 11. M. Scetbon, P. Milanfar and M. Elad, Deep K-SVD Denoising, submitted to IEEE-TPAMI. Michael Elad The Computer-Science Department The Technion 64
Questions? More on these (including these slides and the relevant papers) can be found in http: //www. cs. technion. ac. il/~elad Michael Elad The Computer-Science Department The Technion
- Role modeling theory
- Relational vs dimensional data modeling
- Sparse matrix in data structure
- Incidence matrix
- Best practice etl architecture
- Data and process modeling
- Describe data and process modeling concepts and tools
- Data vault pros and cons
- The emigree by carol rumens
- Its halloween its halloween the moon is full and bright
- Sparse conditional constant propagation
- Suatu array dikatakan upper triangular jika
- Sparse matrix operator kernel emissions
- Sprand matlab
- Sparse matrix
- Sparse conditional constant propagation
- On single image scale-up using sparse-representations
- Primary index is dense or sparse
- Sparse pca
- Confronto dante petrarca
- Tero karras
- Arid region with sparse to almost noneexistent vegetation
- Patterns of sprawl chapter 10 answers
- Sparse solution
- Sparse matrix
- Must not be a sparse array item
- Sparse matrix
- Deklarasi array x adalah int a 2 4 5
- Lookup stage in datastage
- Sparse tableau analysis
- Extensor: an accelerator for sparse tensor algebra
- Efficient sparse voxel octrees
- Scalar replacement of aggregates
- Direct methods for sparse linear systems
- Sparse conditional constant propagation
- Sparse haptic proxy
- Smolyak sparse grid
- Yale representation of sparse matrix
- Sparse tableau analysis
- Sparse convolutional neural networks
- Raphael yuster
- Sparse voxel dag
- Matlab sparse matrix multiplication
- Voi ch ascoltate in rime sparse il suono figure retoriche
- Sparse matrix multiplication cuda
- Fast matrix multiplication
- To every record
- Modeling relational data with graph convolutional networks
- Idefix notation
- Data modeling using entity relationship model
- Data warehouse modeling tutorial
- Modeling data in the organization
- Modeling data in the organization
- Link table qlikview
- Vhdl data flow modeling
- Oltp data modeling
- Modeling real world data with sinusoidal functions
- Modeling distributions of data
- Eclipse data modeling
- Data flow modeling in verilog examples