Timezone: »
We study the problem of inverting a deep generative model with ReLU activations. Inversion corresponds to finding a latent code vector that explains observed measurements as much as possible. In most prior works this is performed by attempting to solve a non-convex optimization problem involving the generator. In this paper we obtain several novel theoretical results for the inversion problem.
We show that for the realizable case, single layer inversion can be performed exactly in polynomial time, by solving a linear program. Further, we show that for two layers, inversion is NP-hard to recover binary latent code (even for the realizable case) and the pre-image set can be non-convex.
For generative models of arbitrary depth, we show that exact recovery is possible in polynomial time with high probability, if the layers are expanding and the weights are randomly selected. Very recent work analyzed the same problem for gradient descent inversion. Their analysis requires significantly higher expansion (logarithmic in the latent dimension) while our proposed algorithm can provably reconstruct even with constant factor expansion. We also provide provable error bounds for different norms for reconstructing noisy observations. Our empirical validation demonstrates that we obtain better reconstructions when the latent dimension is large.
Author Information
Qi Lei (University of Texas at Austin)
Ajil Jalal (University of Texas at Austin)
Inderjit Dhillon (UT Austin & Amazon)
Alex Dimakis (University of Texas, Austin)
More from the Same Authors
-
2022 : Score-based Seismic Inverse Problems »
Sriram Ravula · Dimitri Voytan · Elad Liebman · Ram Tuvi · Yash Gandhi · Hamza Ghani · Alex Ardel · Mrinal Sen · Alex Dimakis -
2022 : Differentially Private Federated Learning with Normalized Updates »
Rudrajit Das · Abolfazl Hashemi · Sujay Sanghavi · Inderjit Dhillon -
2022 : HotProtein: A Novel Framework for Protein Thermostability Prediction and Editing »
Tianlong Chen · Chengyue Gong · Daniel Diaz · Xuxi Chen · Jordan Wells · Qiang Liu · Zhangyang Wang · Andrew Ellington · Alex Dimakis · Adam Klivans -
2022 : Discovering the Hidden Vocabulary of DALLE-2 »
Giannis Daras · Alex Dimakis -
2022 : Multiresolution Textual Inversion »
Giannis Daras · Alex Dimakis -
2023 Poster: Ambient Diffusion: Learning Clean Distributions from Corrupted Data »
Giannis Daras · Kulin Nitinkumar Shah · Yuval Dagan · Aravind Gollakota · Alex Dimakis · Adam Klivans -
2023 Poster: Solving Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models »
Litu Rout · Negin Raoof · Giannis Daras · Constantine Caramanis · Alex Dimakis · Sanjay Shakkottai -
2023 Poster: Block Low-Rank Preconditioner with Shared Basis for Stochastic Optimization »
Jui-Nan Yen · Sai Surya Duvvuri · Inderjit Dhillon · Cho-Jui Hsieh -
2023 Poster: Martingale Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent »
Giannis Daras · Yuval Dagan · Alex Dimakis · Constantinos Daskalakis -
2023 Poster: A Computationally Efficient Sparsified Online Newton Method »
Fnu Devvrit · Sai Surya Duvvuri · Rohan Anil · Vineet Gupta · Cho-Jui Hsieh · Inderjit Dhillon -
2023 Poster: DataComp: In search of the next generation of multimodal datasets »
Samir Yitzhak Gadre · Gabriel Ilharco · Alex Fang · Jonathan Hayase · Georgios Smyrnis · Thao Nguyen · Ryan Marten · Mitchell Wortsman · Dhruba Ghosh · Jieyu Zhang · Eyal Orgad · Rahim Entezari · Giannis Daras · Sarah Pratt · Vivek Ramanujan · Yonatan Bitton · Kalyani Marathe · Stephen Mussmann · Richard Vencu · Mehdi Cherti · Ranjay Krishna · Pang Wei Koh · Olga Saukh · Alexander Ratner · Shuran Song · Hannaneh Hajishirzi · Ali Farhadi · Romain Beaumont · Sewoong Oh · Alex Dimakis · Jenia Jitsev · Yair Carmon · Vaishaal Shankar · Ludwig Schmidt -
2023 Oral: DataComp: In search of the next generation of multimodal datasets »
Samir Yitzhak Gadre · Gabriel Ilharco · Alex Fang · Jonathan Hayase · Georgios Smyrnis · Thao Nguyen · Ryan Marten · Mitchell Wortsman · Dhruba Ghosh · Jieyu Zhang · Eyal Orgad · Rahim Entezari · Giannis Daras · Sarah Pratt · Vivek Ramanujan · Yonatan Bitton · Kalyani Marathe · Stephen Mussmann · Richard Vencu · Mehdi Cherti · Ranjay Krishna · Pang Wei Koh · Olga Saukh · Alexander Ratner · Shuran Song · Hannaneh Hajishirzi · Ali Farhadi · Romain Beaumont · Sewoong Oh · Alex Dimakis · Jenia Jitsev · Yair Carmon · Vaishaal Shankar · Ludwig Schmidt -
2022 Poster: Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve »
Giannis Daras · Negin Raoof · Zoi Gkalitsiou · Alex Dimakis -
2022 Poster: Zonotope Domains for Lagrangian Neural Network Verification »
Matt Jordan · Jonathan Hayase · Alex Dimakis · Sewoong Oh -
2022 Poster: S3GC: Scalable Self-Supervised Graph Clustering »
Fnu Devvrit · Aditya Sinha · Inderjit Dhillon · Prateek Jain -
2022 Poster: ELIAS: End-to-End Learning to Index and Search in Large Output Spaces »
Nilesh Gupta · Patrick Chen · Hsiang-Fu Yu · Cho-Jui Hsieh · Inderjit Dhillon -
2021 : Alex Dimakis Talk »
Alex Dimakis -
2021 Poster: How Fine-Tuning Allows for Effective Meta-Learning »
Kurtland Chua · Qi Lei · Jason Lee -
2021 Poster: Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification »
Jiong Zhang · Wei-Cheng Chang · Hsiang-Fu Yu · Inderjit Dhillon -
2021 Poster: Inverse Problems Leveraging Pre-trained Contrastive Representations »
Sriram Ravula · Georgios Smyrnis · Matt Jordan · Alex Dimakis -
2021 Poster: Label Disentanglement in Partition-based Extreme Multilabel Classification »
Xuanqing Liu · Wei-Cheng Chang · Hsiang-Fu Yu · Cho-Jui Hsieh · Inderjit Dhillon -
2021 Poster: Going Beyond Linear RL: Sample Efficient Neural Function Approximation »
Baihe Huang · Kaixuan Huang · Sham Kakade · Jason Lee · Qi Lei · Runzhe Wang · Jiaqi Yang -
2021 Poster: DRONE: Data-aware Low-rank Compression for Large NLP Models »
Patrick Chen · Hsiang-Fu Yu · Inderjit Dhillon · Cho-Jui Hsieh -
2021 Poster: Robust Compressed Sensing MRI with Deep Generative Priors »
Ajil Jalal · Marius Arvinte · Giannis Daras · Eric Price · Alex Dimakis · Jon Tamir -
2021 Poster: Predicting What You Already Know Helps: Provable Self-Supervised Learning »
Jason Lee · Qi Lei · Nikunj Saunshi · JIACHENG ZHUO -
2021 Poster: Optimal Gradient-based Algorithms for Non-concave Bandit Optimization »
Baihe Huang · Kaixuan Huang · Sham Kakade · Jason Lee · Qi Lei · Runzhe Wang · Jiaqi Yang -
2020 : Compressed Sensing with Approximate Priors via Conditional Resampling »
Ajil Jalal -
2020 Poster: SMYRF - Efficient Attention using Asymmetric Clustering »
Giannis Daras · Nikita Kitaev · Augustus Odena · Alex Dimakis -
2020 Poster: Applications of Common Entropy for Causal Inference »
Murat Kocaoglu · Sanjay Shakkottai · Alex Dimakis · Constantine Caramanis · Sriram Vishwanath -
2020 Poster: Exactly Computing the Local Lipschitz Constant of ReLU Networks »
Matt Jordan · Alex Dimakis -
2020 Poster: Robust compressed sensing using generative models »
Ajil Jalal · Liu Liu · Alex Dimakis · Constantine Caramanis -
2019 : Lunch Break and Posters »
Xingyou Song · Elad Hoffer · Wei-Cheng Chang · Jeremy Cohen · Jyoti Islam · Yaniv Blumenfeld · Andreas Madsen · Jonathan Frankle · Sebastian Goldt · Satrajit Chatterjee · Abhishek Panigrahi · Alex Renda · Brian Bartoldson · Israel Birhane · Aristide Baratin · Niladri Chatterji · Roman Novak · Jessica Forde · YiDing Jiang · Yilun Du · Linara Adilova · Michael Kamp · Berry Weinstein · Itay Hubara · Tal Ben-Nun · Torsten Hoefler · Daniel Soudry · Hsiang-Fu Yu · Kai Zhong · Yiming Yang · Inderjit Dhillon · Jaime Carbonell · Yanqing Zhang · Dar Gilboa · Johannes Brandstetter · Alexander R Johansen · Gintare Karolina Dziugaite · Raghav Somani · Ari Morcos · Freddie Kalaitzis · Hanie Sedghi · Lechao Xiao · John Zech · Muqiao Yang · Simran Kaur · Qianli Ma · Yao-Hung Hubert Tsai · Ruslan Salakhutdinov · Sho Yaida · Zachary Lipton · Daniel Roy · Michael Carbin · Florent Krzakala · Lenka Zdeborová · Guy Gur-Ari · Ethan Dyer · Dilip Krishnan · Hossein Mobahi · Samy Bengio · Behnam Neyshabur · Praneeth Netrapalli · Kris Sankaran · Julien Cornebise · Yoshua Bengio · Vincent Michalski · Samira Ebrahimi Kahou · Md Rifat Arefin · Jiri Hron · Jaehoon Lee · Jascha Sohl-Dickstein · Samuel Schoenholz · David Schwab · Dongyu Li · Sang Choe · Henning Petzka · Ashish Verma · Zhichao Lin · Cristian Sminchisescu -
2019 : Opening Remarks »
Reinhard Heckel · Paul Hand · Alex Dimakis · Joan Bruna · Deanna Needell · Richard Baraniuk -
2019 Workshop: Information Theory and Machine Learning »
Shengjia Zhao · Jiaming Song · Yanjun Han · Kristy Choi · Pratyusha Kalluri · Ben Poole · Alex Dimakis · Jiantao Jiao · Tsachy Weissman · Stefano Ermon -
2019 Workshop: Solving inverse problems with deep networks: New architectures, theoretical foundations, and applications »
Reinhard Heckel · Paul Hand · Richard Baraniuk · Joan Bruna · Alex Dimakis · Deanna Needell -
2019 Poster: Provable Non-linear Inductive Matrix Completion »
Kai Zhong · Zhao Song · Prateek Jain · Inderjit Dhillon -
2019 Poster: Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting »
Rajat Sen · Hsiang-Fu Yu · Inderjit Dhillon -
2019 Poster: AutoAssist: A Framework to Accelerate Training of Deep Neural Networks »
Jiong Zhang · Hsiang-Fu Yu · Inderjit Dhillon -
2019 Poster: Provable Certificates for Adversarial Examples: Fitting a Ball in the Union of Polytopes »
Matt Jordan · Justin Lewis · Alex Dimakis -
2019 Poster: Primal-Dual Block Generalized Frank-Wolfe »
Qi Lei · JIACHENG ZHUO · Constantine Caramanis · Inderjit Dhillon · Alex Dimakis -
2019 Poster: Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models »
Shanshan Wu · Sujay Sanghavi · Alex Dimakis -
2019 Spotlight: Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models »
Shanshan Wu · Sujay Sanghavi · Alex Dimakis -
2019 Poster: Learning Distributions Generated by One-Layer ReLU Networks »
Shanshan Wu · Alex Dimakis · Sujay Sanghavi -
2018 : Poster session »
David Zeng · Marzieh S. Tahaei · Shuai Chen · Felix Meister · Meet Shah · Anant Gupta · Ajil Jalal · Eirini Arvaniti · David Zimmerer · Konstantinos Kamnitsas · Pedro Ballester · Nathaniel Braman · Udaya Kumar · Sil C. van de Leemput · Junaid Qadir · Hoel Kervadec · Mohamed Akrout · Adrian Tousignant · Matthew Ng · Raghav Mehta · Miguel Monteiro · Sumana Basu · Jonas Adler · Adrian Dalca · Jizong Peng · Sungyeob Han · Xiaoxiao Li · Karthik Gopinath · Joseph Cheng · Bogdan Georgescu · Kha Gia Quach · Karthik Sarma · David Van Veen -
2018 : Oral session I »
Jonas Adler · Ajil Jalal · Joseph Cheng -
2018 Poster: Experimental Design for Cost-Aware Learning of Causal Graphs »
Erik Lindgren · Murat Kocaoglu · Alex Dimakis · Sriram Vishwanath -
2018 Poster: Hessian-based Analysis of Large Batch Training and Robustness to Adversaries »
Zhewei Yao · Amir Gholami · Qi Lei · Kurt Keutzer · Michael Mahoney -
2017 Workshop: NIPS Highlights (MLTrain), Learn How to code a paper with state of the art frameworks »
Alex Dimakis · Nikolaos Vasiloglou · Guy Van den Broeck · Alexander Ihler · Assaf Araki -
2017 Poster: A Greedy Approach for Budgeted Maximum Inner Product Search »
Hsiang-Fu Yu · Cho-Jui Hsieh · Qi Lei · Inderjit Dhillon -
2017 Poster: Streaming Weak Submodularity: Interpreting Neural Networks on the Fly »
Ethan Elenberg · Alex Dimakis · Moran Feldman · Amin Karbasi -
2017 Oral: Streaming Weak Submodularity: Interpreting Neural Networks on the Fly »
Ethan Elenberg · Alex Dimakis · Moran Feldman · Amin Karbasi -
2017 Poster: Model-Powered Conditional Independence Test »
Rajat Sen · Ananda Theertha Suresh · Karthikeyan Shanmugam · Alex Dimakis · Sanjay Shakkottai -
2016 Poster: Leveraging Sparsity for Efficient Submodular Data Summarization »
Erik Lindgren · Shanshan Wu · Alex Dimakis -
2016 Poster: Asynchronous Parallel Greedy Coordinate Descent »
Yang You · Xiangru Lian · Ji Liu · Hsiang-Fu Yu · Inderjit Dhillon · James Demmel · Cho-Jui Hsieh -
2016 Poster: Single Pass PCA of Matrix Products »
Shanshan Wu · Srinadh Bhojanapalli · Sujay Sanghavi · Alex Dimakis -
2016 Poster: Coordinate-wise Power Method »
Qi Lei · Kai Zhong · Inderjit Dhillon -
2016 Poster: Structured Sparse Regression via Greedy Hard Thresholding »
Prateek Jain · Nikhil Rao · Inderjit Dhillon -
2016 Poster: Mixed Linear Regression with Multiple Components »
Kai Zhong · Prateek Jain · Inderjit Dhillon -
2016 Poster: Temporal Regularized Matrix Factorization for High-dimensional Time Series Prediction »
Hsiang-Fu Yu · Nikhil Rao · Inderjit Dhillon -
2016 Poster: Dual Decomposed Learning with Factorwise Oracle for Structural SVM of Large Output Domain »
Ian En-Hsu Yen · Xiangru Huang · Kai Zhong · Ruohan Zhang · Pradeep Ravikumar · Inderjit Dhillon -
2015 Workshop: Multiresolution methods for large-scale learning »
Inderjit Dhillon · Risi Kondor · Rob Nowak · Michael O'Neil · Nedelina Teneva -
2015 Poster: Orthogonal NMF through Subspace Exploration »
Megasthenis Asteris · Dimitris Papailiopoulos · Alex Dimakis -
2015 Poster: Matrix Completion with Noisy Side Information »
Kai-Yang Chiang · Cho-Jui Hsieh · Inderjit Dhillon -
2015 Poster: Collaborative Filtering with Graph Information: Consistency and Scalable Methods »
Nikhil Rao · Hsiang-Fu Yu · Pradeep Ravikumar · Inderjit Dhillon -
2015 Spotlight: Collaborative Filtering with Graph Information: Consistency and Scalable Methods »
Nikhil Rao · Hsiang-Fu Yu · Pradeep Ravikumar · Inderjit Dhillon -
2015 Spotlight: Matrix Completion with Noisy Side Information »
Kai-Yang Chiang · Cho-Jui Hsieh · Inderjit Dhillon -
2015 Poster: Sparse PCA via Bipartite Matchings »
Megasthenis Asteris · Dimitris Papailiopoulos · Anastasios Kyrillidis · Alex Dimakis -
2015 Poster: Sparse Linear Programming via Primal and Dual Augmented Coordinate Descent »
Ian En-Hsu Yen · Kai Zhong · Cho-Jui Hsieh · Pradeep Ravikumar · Inderjit Dhillon -
2015 Poster: Learning Causal Graphs with Small Interventions »
Karthikeyan Shanmugam · Murat Kocaoglu · Alex Dimakis · Sriram Vishwanath -
2015 Poster: Fixed-Length Poisson MRF: Adding Dependencies to the Multinomial »
David I Inouye · Pradeep Ravikumar · Inderjit Dhillon -
2015 Poster: Consistent Multilabel Classification »
Oluwasanmi Koyejo · Nagarajan Natarajan · Pradeep Ravikumar · Inderjit Dhillon -
2014 Poster: QUIC & DIRTY: A Quadratic Approximation Approach for Dirty Statistical Models »
Cho-Jui Hsieh · Inderjit Dhillon · Pradeep Ravikumar · Stephen Becker · Peder A Olsen -
2014 Poster: Sparse Polynomial Learning and Graph Sketching »
Murat Kocaoglu · Karthikeyan Shanmugam · Alex Dimakis · Adam Klivans -
2014 Poster: Consistent Binary Classification with Generalized Performance Metrics »
Sanmi Koyejo · Nagarajan Natarajan · Pradeep Ravikumar · Inderjit Dhillon -
2014 Poster: Fast Prediction for Large-Scale Kernel Machines »
Cho-Jui Hsieh · Si Si · Inderjit Dhillon -
2014 Poster: Multi-Scale Spectral Decomposition of Massive Graphs »
Si Si · Donghyuk Shin · Inderjit Dhillon · Beresford N Parlett -
2014 Poster: On the Information Theoretic Limits of Learning Ising Models »
Rashish Tandon · Karthikeyan Shanmugam · Pradeep Ravikumar · Alex Dimakis -
2014 Poster: Sparse Random Feature Algorithm as Coordinate Descent in Hilbert Space »
Ian En-Hsu Yen · Ting-Wei Lin · Shou-De Lin · Pradeep Ravikumar · Inderjit Dhillon -
2014 Spotlight: Consistent Binary Classification with Generalized Performance Metrics »
Sanmi Koyejo · Nagarajan Natarajan · Pradeep Ravikumar · Inderjit Dhillon -
2014 Oral: Sparse Polynomial Learning and Graph Sketching »
Murat Kocaoglu · Karthikeyan Shanmugam · Alex Dimakis · Adam Klivans -
2014 Poster: Proximal Quasi-Newton for Computationally Intensive L1-regularized M-estimators »
Kai Zhong · Ian En-Hsu Yen · Inderjit Dhillon · Pradeep Ravikumar -
2014 Poster: Capturing Semantically Meaningful Word Dependencies with an Admixture of Poisson MRFs »
David I Inouye · Pradeep Ravikumar · Inderjit Dhillon -
2014 Poster: Constant Nullspace Strong Convexity and Fast Convergence of Proximal Methods under High-Dimensional Settings »
Ian En-Hsu Yen · Cho-Jui Hsieh · Pradeep Ravikumar · Inderjit Dhillon -
2013 Poster: BIG & QUIC: Sparse Inverse Covariance Estimation for a Million Variables »
Cho-Jui Hsieh · Matyas A Sustik · Inderjit Dhillon · Pradeep Ravikumar · Russell Poldrack -
2013 Oral: BIG & QUIC: Sparse Inverse Covariance Estimation for a Million Variables »
Cho-Jui Hsieh · Matyas A Sustik · Inderjit Dhillon · Pradeep Ravikumar · Russell Poldrack -
2013 Poster: Large Scale Distributed Sparse Precision Estimation »
Huahua Wang · Arindam Banerjee · Cho-Jui Hsieh · Pradeep Ravikumar · Inderjit Dhillon -
2013 Poster: Learning with Noisy Labels »
Nagarajan Natarajan · Inderjit Dhillon · Pradeep Ravikumar · Ambuj Tewari -
2012 Poster: A Divide-and-Conquer Method for Sparse Inverse Covariance Estimation »
Cho-Jui Hsieh · Inderjit Dhillon · Pradeep Ravikumar · Arindam Banerjee -
2011 Poster: Greedy Algorithms for Structurally Constrained High Dimensional Problems »
Ambuj Tewari · Pradeep Ravikumar · Inderjit Dhillon -
2011 Poster: Sparse Inverse Covariance Matrix Estimation Using Quadratic Approximation »
Cho-Jui Hsieh · Matyas A Sustik · Inderjit Dhillon · Pradeep Ravikumar -
2011 Poster: Nearest Neighbor based Greedy Coordinate Descent »
Inderjit Dhillon · Pradeep Ravikumar · Ambuj Tewari -
2011 Poster: Orthogonal Matching Pursuit with Replacement »
Prateek Jain · Ambuj Tewari · Inderjit Dhillon -
2010 Spotlight: Guaranteed Rank Minimization via Singular Value Projection »
Prateek Jain · Raghu Meka · Inderjit Dhillon -
2010 Poster: Guaranteed Rank Minimization via Singular Value Projection »
Prateek Jain · Raghu Meka · Inderjit Dhillon -
2010 Spotlight: Inductive Regularized Learning of Kernel Functions »
Prateek Jain · Brian Kulis · Inderjit Dhillon -
2010 Poster: Inductive Regularized Learning of Kernel Functions »
Prateek Jain · Brian Kulis · Inderjit Dhillon -
2009 Poster: Matrix Completion from Power-Law Distributed Samples »
Raghu Meka · Prateek Jain · Inderjit Dhillon -
2008 Poster: Online Metric Learning and Fast Similarity Search »
Prateek Jain · Brian Kulis · Inderjit Dhillon · Kristen Grauman -
2008 Oral: Online Metric Learning and Fast Similarity Search »
Prateek Jain · Brian Kulis · Inderjit Dhillon · Kristen Grauman -
2006 Poster: Differential Entropic Clustering of Multivariate Gaussians »
Jason V Davis · Inderjit Dhillon