Timezone: »
There is a long history of algorithmic development for solving inverse problems arising in sensing and imaging systems and beyond. Examples include medical and computational imaging, compressive sensing, as well as community detection in networks. Until recently, most algorithms for solving inverse problems in the imaging and network sciences were based on static signal models derived from physics or intuition, such as wavelets or sparse representations.
Today, the best performing approaches for the aforementioned image reconstruction and sensing problems are based on deep learning, which learn various elements of the method including i) signal representations, ii) stepsizes and parameters of iterative algorithms, iii) regularizers, and iv) entire inverse functions. For example, it has recently been shown that solving a variety of inverse problems by transforming an iterative, physicsbased algorithm into a deep network whose parameters can be learned from training data, offers faster convergence and/or a better quality solution. Moreover, even with very little or no learning, deep neural networks enable superior performance for classical linear inverse problems such as denoising and compressive sensing. Motivated by those success stories, researchers are redesigning traditional imaging and sensing systems.
However, the field is mostly wide open with a range of theoretical and practical questions unanswered. In particular, deepneural network based approaches often lack the guarantees of the traditional physics based methods, and while typically superior can make drastic reconstruction errors, such as fantasizing a tumor in an MRI reconstruction.
This workshop aims at bringing together theoreticians and practitioners in order to chart out recent advances and discuss new directions in deep neural network based approaches for solving inverse problems in the imaging and network sciences.
Fri 8:30 a.m.  8:35 a.m.

Opening Remarks

Reinhard Heckel, Paul Hand, Alex Dimakis, Joan Bruna, Deanna Needell, Richard Baraniuk 
Fri 8:40 a.m.  9:10 a.m.

The spiked matrix model with generative priors
(Talk)
»
Using a lowdimensional parametrization of signals is a generic and powerful way to enhance performance in signal processing and statistical inference. A very popular and widely explored type of dimensionality reduction is sparsity; another type is generative modelling of signal distributions. Generative models based on neural networks, such as GANs or variational autoencoders, are particularly performant and are gaining on applicability. In this paper we study spiked matrix models, where a lowrank matrix is observed through a noisy channel. This problem with sparse structure of the spikes has attracted broad attention in the past literature. Here, we replace the sparsity assumption by generative modelling, and investigate the consequences on statistical and algorithmic properties. We analyze the Bayesoptimal performance under specific generative models for the spike. In contrast with the sparsity assumption, we do not observe regions of parameters where statistical performance is superior to the best known algorithmic performance. We show that in the analyzed cases the approximate message passing algorithm is able to reach optimal performance. We also design enhanced spectral algorithms and analyze their performance and thresholds using random matrix theory, showing their superiority to the classical principal component analysis. We complement our theoretical results by illustrating the performance of the spectral algorithms when the spikes come from real datasets. 
Lenka Zdeborová 
Fri 9:10 a.m.  9:40 a.m.

Robust OneBit Recovery via ReLU Generative Networks: Improved Statistical Rate and Global Landscape Analysis
(Talk)
»
We study the robust onebit compressed sensing problem whose goal is to design an algorithm that faithfully recovers any sparse target vector $\theta_0\in\mathbb{R}^d$ \emph{uniformly} from $m$ quantized noisy measurements. Under the assumption that the measurements are subGaussian, to recover any $k$sparse $\theta_0$ ($k\ll d$) \emph{uniformly} up to an error $\varepsilon$ with high probability, the best known computationally tractable algorithm requires\footnote{Here, an algorithm is ``computationally tractable'' if it has provable convergence guarantees. The notation $\tilde{\mathcal{O}}(\cdot)$ omits a logarithm factor of $\varepsilon^{1}$.} $m\geq\tilde{\mathcal{O}}(k\log d/\varepsilon^4)$. In this paper, we consider a new framework for the onebit sensing problem where the sparsity is implicitly enforced via mapping a low dimensional representation $x_0$ through a known $n$layer ReLU generative network $G:\mathbb{R}^k\rightarrow\mathbb{R}^d$. Such a framework poses lowdimensional priors on $\theta_0$ without a known basis. We propose to recover the target $G(x_0)$ via an unconstrained empirical risk minimization (ERM) problem under a much weaker \emph{subexponential measurement assumption}. For such a problem, we establish a joint statistical and computational analysis. In particular, we prove that the ERM estimator in this new framework achieves an improved statistical rate of $m=\tilde{\mathcal{O}} (kn\log d /\epsilon^2)$ recovering any $G(x_0)$ uniformly up to an error $\varepsilon$. Moreover, from the lens of computation, despite nonconvexity, we prove that the objective of our ERM problem has no spurious stationary point, that is, any stationary point is equally good for recovering the true target up to scaling with a certain accuracy. Our analysis sheds some light on the possibility of inverting a deep generative model under partial and quantized measurements, complementing the recent success of using deep generative models for inverse problems.

Shuang Qiu, Xiaohan Wei, Zhuoran Yang 
Fri 9:40 a.m.  10:30 a.m.

Coffee Break
(Break)


Fri 10:30 a.m.  11:00 a.m.

Computational microscopy in scattering media
(Talk)
»
Computational imaging involves the joint design of imaging system hardware and software, optimizing across the entire pipeline from acquisition to reconstruction. Computers can replace bulky and expensive optics by solving computational inverse problems. This talk will describe new microscopes that use computational imaging to enable 3D fluorescence and phase measurement using image reconstruction algorithms that are based on largescale nonlinear nonconvex optimization combined with unrolled neural networks. We further discuss engineering of data capture for computational microscopes by endtoend learned design. 
Laura Waller 
Fri 11:00 a.m.  11:30 a.m.

Denoising via Early Stopping
(Talk)

Mahdi Soltanolkotabi 
Fri 11:30 a.m.  12:00 p.m.

Neural Reparameterization Improves Structural Optimization
(Talk)
»
Structural optimization is a popular method for designing objects such as bridge trusses, airplane wings, and optical devices. Unfortunately, the quality of solutions depends heavily on how the problem is parameterized. In this paper, we propose using the implicit bias over functions induced by neural networks to improve the parameterization of structural optimization. Rather than directly optimizing densities on a grid, we instead optimize the parameters of a neural network which outputs those densities. This reparameterization leads to different and often better solutions. On a selection of 116 structural optimization tasks, our approach produces an optimal design 50% more often than the best baseline method. 
Stephan Hoyer, Jascha SohlDickstein, Sam Greydanus 
Fri 12:00 p.m.  2:00 p.m.

Lunch Break
(Break)


Fri 2:00 p.m.  2:30 p.m.

LearningBased LowRank Approximations
(Talk)

Piotr Indyk 
Fri 2:30 p.m.  3:00 p.m.

Blind Denoising, SelfSupervision, and Implicit Inverse Problems
(Talk)
»
We will discuss a selfsupervised approach to the foundational inverse problem of denoising (Noise2Self). By taking advantage of statistical independence in the noise, we can estimate the meansquare error for a large class of deep architectures without access to ground truth. This allows us to train a neural network to denoise from noisy data alone, and also to compare between architectures, selecting one which will produce images with the lowest MSE. However, architectures with the same MSE performance can produce qualitatively different results, i.e., the hypersurface of images with fixed MSE is very heterogeneous. We will discuss ongoing work in understanding the types of artifacts which different denoising architectures give rise to. 
Joshua Batson 
Fri 3:00 p.m.  3:30 p.m.

Learning Regularizers from Data
(Talk)
»
Regularization techniques are widely employed in the solution of inverse problems in data analysis and scientific computing due to their effectiveness in addressing difficulties due to illposedness. In their most common manifestation, these methods take the form of penalty functions added to the objective in variational approaches for solving inverse problems. The purpose of the penalty function is to induce a desired structure in the solution, and these functions are specified based on prior domainspecific expertise. We consider the problem of learning suitable regularization functions from data in settings in which precise domain knowledge is not directly available; the objective is to identify a regularizer to promote the type of structure contained in the data. The regularizers obtained using our framework are specified as convex functions that can be computed efficiently via semidefinite programming. Our approach for learning such semidefinite regularizers combines recent techniques for rank minimization problems along with the Operator Sinkhorn procedure. (Joint work with Yong Sheng Soh) 
Venkat Chandrasekaran 
Fri 4:15 p.m.  6:00 p.m.

Poster Session

Jonathan Scarlett, Piotr Indyk, Ali Vakilian, Adrian Weller, Partha P Mitra, Benjamin Aubin, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová, Kristina Monakhova, Joshua Yurtsever, Laura Waller, Hendrik Sommerhoff, Michael Moeller, Rushil Anirudh, Shuang Qiu, Xiaohan Wei, Zhuoran Yang, Jayaraman Thiagarajan, Salman Asif, Michael Gillhofer, Johannes Brandstetter, Sepp Hochreiter, Felix Petersen, Dhruv Patel, Assad Oberai, Akshay Kamath, Sushrut Karmalkar, Eric Price, Ali Ahmed, Zahra Kadkhodaie, Sreyas Mohan, Eero Simoncelli, Carlos FernandezGranda, Oscar Leong, Wesam Sakla, Rebecca Willett, Stephan Hoyer, Jascha SohlDickstein, Sam Greydanus, Gauri Jagatap, Chinmay Hegde, Michael Kellman, Jon Tamir, Numan Laanait, Ousmane Dia, Mirco Ravanelli, Jonathan Binas, Negar Rostamzadeh, Shirin Jalali, Tiantian Fang, Alex Schwing, Sébastien Lachapelle, Philippe Brouillard, Tristan Deleu, Simon LacosteJulien, Stella Yu, Arya Mazumdar, Ankit Singh Rawat, Yue Zhao, Jianshu Chen, Rebecca Li, Hubert Ramsauer, Gabrio Rizzuti, Nikolaos Mitsakos, Dingzhou Cao, Thomas Strohmer, Yang Li, Pei Peng, Greg Ongie

Author Information
Reinhard Heckel (TUM)
Paul Hand (Northeastern University)
Richard Baraniuk (Rice University)
Joan Bruna (NYU)
Alex Dimakis (University of Texas, Austin)
Deanna Needell (UCLA)
More from the Same Authors

2021 Workshop: Workshop on Deep Learning and Inverse Problems »
Reinhard Heckel · Paul Hand · Rebecca Willett · christopher metzler · Mahdi Soltanolkotabi 
2020 Workshop: Workshop on Deep Learning and Inverse Problems »
Reinhard Heckel · Paul Hand · Richard Baraniuk · Lenka Zdeborová · Soheil Feizi 
2020 Poster: A meanfield analysis of twoplayer zerosum games »
Carles DomingoEnrich · Samy Jelassi · Arthur Mensch · Grant Rotskoff · Joan Bruna 
2020 Poster: Can Graph Neural Networks Count Substructures? »
Zhengdao Chen · Lei Chen · Soledad Villar · Joan Bruna 
2020 Poster: Analytical Probability Distributions and Exact ExpectationMaximization for Deep Generative Networks »
Randall Balestriero · Sebastien PARIS · Richard Baraniuk 
2020 Poster: SMYRF  Efficient Attention using Asymmetric Clustering »
Giannis Daras · Nikita Kitaev · Augustus Odena · Alexandros Dimakis 
2020 Session: Orals & Spotlights Track 26: Graph/Relational/Theory »
Joan Bruna · Cassio de Campos 
2020 Poster: MomentumRNN: Integrating Momentum into Recurrent Neural Networks »
Tan Nguyen · Richard Baraniuk · Andrea Bertozzi · Stanley Osher · Bao Wang 
2020 Poster: IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method »
Yossi Arjevani · Joan Bruna · Bugra Can · Mert Gurbuzbalaban · Stefanie Jegelka · Hongzhou Lin 
2020 Poster: Applications of Common Entropy for Causal Inference »
Murat Kocaoglu · Sanjay Shakkottai · Alexandros Dimakis · Constantine Caramanis · Sriram Vishwanath 
2020 Spotlight: IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method »
Yossi Arjevani · Joan Bruna · Bugra Can · Mert Gurbuzbalaban · Stefanie Jegelka · Hongzhou Lin 
2020 Poster: Exactly Computing the Local Lipschitz Constant of ReLU Networks »
Matt Jordan · Alexandros Dimakis 
2020 Poster: Nonasymptotic Guarantees for Spiked Matrix Recovery with Generative Priors »
Jorio Cocola · Paul Hand · Vlad Voroninski 
2020 Poster: A Dynamical Central Limit Theorem for Shallow Neural Networks »
Zhengdao Chen · Grant Rotskoff · Joan Bruna · Eric VandenEijnden 
2020 Poster: Robust compressed sensing using generative models »
Ajil Jalal · Liu Liu · Alexandros Dimakis · Constantine Caramanis 
2019 Workshop: Information Theory and Machine Learning »
Shengjia Zhao · Jiaming Song · Yanjun Han · Kristy Choi · Pratyusha Kalluri · Ben Poole · Alexandros Dimakis · Jiantao Jiao · Tsachy Weissman · Stefano Ermon 
2019 Poster: Gradient Dynamics of Shallow Univariate ReLU Networks »
Francis Williams · Matthew Trager · Daniele Panozzo · Claudio Silva · Denis Zorin · Joan Bruna 
2019 Poster: On the Expressive Power of Deep Polynomial Neural Networks »
Joe Kileel · Matthew Trager · Joan Bruna 
2019 Poster: Global Guarantees for Blind Demodulation with Generative Priors »
Paul Hand · Babhru Joshi 
2019 Poster: Inverting Deep Generative models, One layer at a time »
Qi Lei · Ajil Jalal · Inderjit Dhillon · Alexandros Dimakis 
2019 Poster: Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias »
Stéphane d'Ascoli · Levent Sagun · Giulio Biroli · Joan Bruna 
2019 Poster: Provable Certificates for Adversarial Examples: Fitting a Ball in the Union of Polytopes »
Matt Jordan · Justin Lewis · Alexandros Dimakis 
2019 Poster: PrimalDual Block Generalized FrankWolfe »
Qi Lei · JIACHENG ZHUO · Constantine Caramanis · Inderjit Dhillon · Alexandros Dimakis 
2019 Poster: On the equivalence between graph isomorphism testing and function approximation with GNNs »
Zhengdao Chen · Soledad Villar · Lei Chen · Joan Bruna 
2019 Poster: Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models »
Shanshan Wu · Sujay Sanghavi · Alexandros Dimakis 
2019 Spotlight: Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models »
Shanshan Wu · Sujay Sanghavi · Alexandros Dimakis 
2019 Poster: Stability of Graph Scattering Transforms »
Fernando Gama · Alejandro Ribeiro · Joan Bruna 
2019 Poster: Learning Distributions Generated by OneLayer ReLU Networks »
Shanshan Wu · Alexandros Dimakis · Sujay Sanghavi 
2019 Poster: The Geometry of Deep Networks: Power Diagram Subdivision »
Randall Balestriero · Romain Cosentino · Behnaam Aazhang · Richard Baraniuk 
2018 Workshop: Integration of Deep Learning Theories »
Richard Baraniuk · Anima Anandkumar · Stephane Mallat · Ankit Patel · nhật Hồ 
2018 Workshop: Machine Learning for Geophysical & Geochemical Signals »
Laura PyrakNolte · James Rustad · Richard Baraniuk 
2018 Poster: A convex program for bilinear inversion of sparse vectors »
Alireza Aghasi · Ali Ahmed · Paul Hand · Babhru Joshi 
2018 Poster: Experimental Design for CostAware Learning of Causal Graphs »
Erik Lindgren · Murat Kocaoglu · Alexandros Dimakis · Sriram Vishwanath 
2018 Poster: Blind Deconvolutional Phase Retrieval via Convex Programming »
Ali Ahmed · Alireza Aghasi · Paul Hand 
2018 Spotlight: Blind Deconvolutional Phase Retrieval via Convex Programming »
Ali Ahmed · Alireza Aghasi · Paul Hand 
2018 Poster: Phase Retrieval Under a Generative Prior »
Paul Hand · Oscar Leong · Vlad Voroninski 
2018 Oral: Phase Retrieval Under a Generative Prior »
Paul Hand · Oscar Leong · Vlad Voroninski 
2017 Workshop: NIPS Highlights (MLTrain), Learn How to code a paper with state of the art frameworks »
Alexandros Dimakis · Nikolaos Vasiloglou · Guy Van den Broeck · Alexander Ihler · Assaf Araki 
2017 Workshop: Advances in Modeling and Learning Interactions from Complex Data »
Gautam Dasarathy · Mladen Kolar · Richard Baraniuk 
2017 Poster: Streaming Weak Submodularity: Interpreting Neural Networks on the Fly »
Ethan Elenberg · Alexandros Dimakis · Moran Feldman · Amin Karbasi 
2017 Oral: Streaming Weak Submodularity: Interpreting Neural Networks on the Fly »
Ethan Elenberg · Alexandros Dimakis · Moran Feldman · Amin Karbasi 
2017 Poster: Learned DAMP: Principled Neural Network based Compressive Image Recovery »
Chris Metzler · Ali Mousavi · Richard Baraniuk 
2017 Poster: ModelPowered Conditional Independence Test »
Rajat Sen · Ananda Theertha Suresh · Karthikeyan Shanmugam · Alexandros Dimakis · Sanjay Shakkottai 
2017 Tutorial: Geometric Deep Learning on Graphs and Manifolds »
Michael Bronstein · Joan Bruna · arthur szlam · Xavier Bresson · Yann LeCun 
2016 Workshop: Machine Learning for Education »
Richard Baraniuk · Jiquan Ngiam · Christoph Studer · Phillip Grimaldi · Andrew Lan 
2016 Poster: Leveraging Sparsity for Efficient Submodular Data Summarization »
Erik Lindgren · Shanshan Wu · Alexandros Dimakis 
2016 Poster: A Probabilistic Framework for Deep Learning »
Ankit Patel · Tan Nguyen · Richard Baraniuk 
2016 Poster: Single Pass PCA of Matrix Products »
Shanshan Wu · Srinadh Bhojanapalli · Sujay Sanghavi · Alexandros Dimakis 
2015 Poster: Orthogonal NMF through Subspace Exploration »
Megasthenis Asteris · Dimitris Papailiopoulos · Alexandros Dimakis 
2015 Poster: Sparse PCA via Bipartite Matchings »
Megasthenis Asteris · Dimitris Papailiopoulos · Anastasios Kyrillidis · Alexandros Dimakis 
2015 Poster: Learning Causal Graphs with Small Interventions »
Karthikeyan Shanmugam · Murat Kocaoglu · Alexandros Dimakis · Sriram Vishwanath 
2014 Workshop: Human Propelled Machine Learning »
Richard Baraniuk · Michael Mozer · Divyanshu Vats · Christoph Studer · Andrew E Waters · Andrew Lan 
2014 Poster: Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation »
Emily Denton · Wojciech Zaremba · Joan Bruna · Yann LeCun · Rob Fergus 
2014 Poster: Sparse Polynomial Learning and Graph Sketching »
Murat Kocaoglu · Karthikeyan Shanmugam · Alexandros Dimakis · Adam Klivans 
2014 Poster: On the Information Theoretic Limits of Learning Ising Models »
Rashish Tandon · Karthikeyan Shanmugam · Pradeep Ravikumar · Alexandros Dimakis 
2014 Oral: Sparse Polynomial Learning and Graph Sketching »
Murat Kocaoglu · Karthikeyan Shanmugam · Alexandros Dimakis · Adam Klivans 
2013 Poster: When in Doubt, SWAP: HighDimensional Sparse Recovery from Correlated Measurements »
Divyanshu Vats · Richard Baraniuk 
2011 Poster: SpaRCS: Recovering lowrank and sparse matrices from compressive measurements »
Andrew E Waters · Aswin C Sankaranarayanan · Richard Baraniuk 
2009 Workshop: Manifolds, sparsity, and structured models: When can lowdimensional geometry really help? »
Richard Baraniuk · Volkan Cevher · Mark A Davenport · Piotr Indyk · Bruno Olshausen · Michael B Wakin 
2008 Poster: Sparse Signal Recovery Using Markov Random Fields »
Volkan Cevher · Marco F Duarte · Chinmay Hegde · Richard Baraniuk 
2008 Spotlight: Sparse Signal Recovery Using Markov Random Fields »
Volkan Cevher · Marco F Duarte · Chinmay Hegde · Richard Baraniuk 
2007 Poster: Random Projections for Manifold Learning »
Chinmay Hegde · Richard Baraniuk