Timezone: »
A learned generative model often produces biased statistics relative to the underlying data distribution. A standard technique to correct this bias is importance sampling, where samples from the model are weighted by the likelihood ratio under model and true distributions. When the likelihood ratio is unknown, it can be estimated by training a probabilistic classifier to distinguish samples from the two distributions. We show that this likelihood-free importance weighting method induces a new energy-based model and employ it to correct for the bias in existing models. We find that this technique consistently improves standard goodness-of-fit metrics for evaluating the sample quality of state-of-the-art deep generative models, suggesting reduced bias. Finally, we demonstrate its utility on representative applications in a) data augmentation for classification using generative adversarial networks, and b) model-based policy evaluation using off-policy data.
Author Information
Aditya Grover (Stanford University)
Jiaming Song (Stanford University)
I am a first year Ph.D. student in Stanford University. I think about problems in machine learning and deep learning under the supervision of Stefano Ermon. I did my undergrad at Tsinghua University, where I was lucky enough to collaborate with Jun Zhu and Lawrence Carin on scalable Bayesian machine learning.
Ashish Kapoor (Microsoft)
Kenneth Tran (Microsoft Research)
Alekh Agarwal (Microsoft Research)
Eric Horvitz (Microsoft Research)
Stefano Ermon (Stanford)
More from the Same Authors
-
2020 Workshop: Cooperative AI »
Thore Graepel · Dario Amodei · Vincent Conitzer · Allan Dafoe · Gillian Hadfield · Eric Horvitz · Sarit Kraus · Kate Larson · Yoram Bachrach -
2020 Poster: Improved Techniques for Training Score-Based Generative Models »
Yang Song · Stefano Ermon -
2020 Poster: Probabilistic Circuits for Variational Inference in Discrete Graphical Models »
Andy Shih · Stefano Ermon -
2020 Poster: Efficient Learning of Generative Models via Finite-Difference Score Matching »
Tianyu Pang · Kun Xu · Chongxuan LI · Yang Song · Stefano Ermon · Jun Zhu -
2020 Poster: Belief Propagation Neural Networks »
Jonathan Kuck · Shuvam Chakraborty · Hao Tang · Rachel Luo · Jiaming Song · Ashish Sabharwal · Stefano Ermon -
2020 Poster: HiPPO: Recurrent Memory with Optimal Polynomial Projections »
Albert Gu · Tri Dao · Stefano Ermon · Atri Rudra · Christopher Ré -
2020 Spotlight: HiPPO: Recurrent Memory with Optimal Polynomial Projections »
Albert Gu · Tri Dao · Stefano Ermon · Atri Rudra · Christopher Ré -
2020 Poster: Autoregressive Score Matching »
Chenlin Meng · Lantao Yu · Yang Song · Jiaming Song · Stefano Ermon -
2020 Poster: Do Adversarially Robust ImageNet Models Transfer Better? »
Hadi Salman · Andrew Ilyas · Logan Engstrom · Ashish Kapoor · Aleksander Madry -
2020 Poster: Policy Improvement via Imitation of Multiple Oracles »
Ching-An Cheng · Andrey Kolobov · Alekh Agarwal -
2020 Spotlight: Policy Improvement via Imitation of Multiple Oracles »
Ching-An Cheng · Andrey Kolobov · Alekh Agarwal -
2020 Oral: Do Adversarially Robust ImageNet Models Transfer Better? »
Hadi Salman · Andrew Ilyas · Logan Engstrom · Ashish Kapoor · Aleksander Madry -
2020 Poster: Denoised Smoothing: A Provable Defense for Pretrained Classifiers »
Hadi Salman · Mingjie Sun · Greg Yang · Ashish Kapoor · J. Zico Kolter -
2020 Poster: FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs »
Alekh Agarwal · Sham Kakade · Akshay Krishnamurthy · Wen Sun -
2020 Poster: PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning »
Alekh Agarwal · Mikael Henaff · Sham Kakade · Wen Sun -
2020 Poster: Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates »
Wenhao Luo · Wen Sun · Ashish Kapoor -
2020 Spotlight: Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates »
Wenhao Luo · Wen Sun · Ashish Kapoor -
2020 Oral: FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs »
Alekh Agarwal · Sham Kakade · Akshay Krishnamurthy · Wen Sun -
2020 Poster: Diversity can be Transferred: Output Diversification for White- and Black-box Attacks »
Yusuke Tashiro · Yang Song · Stefano Ermon -
2020 Poster: Safe Reinforcement Learning via Curriculum Induction »
Matteo Turchetta · Andrey Kolobov · Shital Shah · Andreas Krause · Alekh Agarwal -
2020 Poster: MOPO: Model-based Offline Policy Optimization »
Tianhe Yu · Garrett Thomas · Lantao Yu · Stefano Ermon · James Zou · Sergey Levine · Chelsea Finn · Tengyu Ma -
2020 Poster: Multi-label Contrastive Predictive Coding »
Jiaming Song · Stefano Ermon -
2020 Poster: Provably Good Batch Off-Policy Reinforcement Learning Without Great Exploration »
Yao Liu · Adith Swaminathan · Alekh Agarwal · Emma Brunskill -
2020 Spotlight: Safe Reinforcement Learning via Curriculum Induction »
Matteo Turchetta · Andrey Kolobov · Shital Shah · Andreas Krause · Alekh Agarwal -
2020 Oral: Multi-label Contrastive Predictive Coding »
Jiaming Song · Stefano Ermon -
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: Characterizing Bias in Classifiers using Generative Models »
Daniel McDuff · Shuang Ma · Yale Song · Ashish Kapoor -
2019 Poster: Efficient Forward Architecture Search »
Hanzhang Hu · John Langford · Rich Caruana · Saurajit Mukherjee · Eric Horvitz · Debadeepta Dey -
2019 Poster: Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations. »
Sawyer Birnbaum · Volodymyr Kuleshov · Zayd Enam · Pang Wei Koh · Stefano Ermon -
2019 Poster: MintNet: Building Invertible Neural Networks with Masked Convolutions »
Yang Song · Chenlin Meng · Stefano Ermon -
2019 Poster: Meta-Inverse Reinforcement Learning with Probabilistic Context Variables »
Lantao Yu · Tianhe Yu · Chelsea Finn · Stefano Ermon -
2019 Poster: Approximating the Permanent by Sampling from Adaptive Partitions »
Jonathan Kuck · Tri Dao · Hamid Rezatofighi · Ashish Sabharwal · Stefano Ermon -
2019 Poster: Generative Modeling by Estimating Gradients of the Data Distribution »
Yang Song · Stefano Ermon -
2019 Poster: Staying up to Date with Online Content Changes Using Reinforcement Learning for Scheduling »
Andrey Kolobov · Yuval Peres · Cheng Lu · Eric Horvitz -
2019 Oral: Generative Modeling by Estimating Gradients of the Data Distribution »
Yang Song · Stefano Ermon -
2018 Workshop: Relational Representation Learning »
Aditya Grover · Paroma Varma · Frederic Sala · Christopher Ré · Jennifer Neville · Stefano Ermon · Steven Holtzen -
2018 Poster: Streamlining Variational Inference for Constraint Satisfaction Problems »
Aditya Grover · Tudor Achim · Stefano Ermon -
2018 Poster: Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance »
Neal Jean · Sang Michael Xie · Stefano Ermon -
2018 Poster: Multi-Agent Generative Adversarial Imitation Learning »
Jiaming Song · Hongyu Ren · Dorsa Sadigh · Stefano Ermon -
2018 Poster: On Oracle-Efficient PAC RL with Rich Observations »
Christoph Dann · Nan Jiang · Akshay Krishnamurthy · Alekh Agarwal · John Langford · Robert Schapire -
2018 Poster: Constructing Unrestricted Adversarial Examples with Generative Models »
Yang Song · Rui Shu · Nate Kushman · Stefano Ermon -
2018 Spotlight: On Oracle-Efficient PAC RL with Rich Observations »
Christoph Dann · Nan Jiang · Akshay Krishnamurthy · Alekh Agarwal · John Langford · Robert Schapire -
2018 Poster: Bias and Generalization in Deep Generative Models: An Empirical Study »
Shengjia Zhao · Hongyu Ren · Arianna Yuan · Jiaming Song · Noah Goodman · Stefano Ermon -
2018 Spotlight: Bias and Generalization in Deep Generative Models: An Empirical Study »
Shengjia Zhao · Hongyu Ren · Arianna Yuan · Jiaming Song · Noah Goodman · Stefano Ermon -
2018 Poster: Amortized Inference Regularization »
Rui Shu · Hung Bui · Shengjia Zhao · Mykel J Kochenderfer · Stefano Ermon -
2017 Workshop: OPT 2017: Optimization for Machine Learning »
Suvrit Sra · Sashank J. Reddi · Alekh Agarwal · Benjamin Recht -
2017 Poster: Off-policy evaluation for slate recommendation »
Adith Swaminathan · Akshay Krishnamurthy · Alekh Agarwal · Miro Dudik · John Langford · Damien Jose · Imed Zitouni -
2017 Oral: Off-policy evaluation for slate recommendation »
Adith Swaminathan · Akshay Krishnamurthy · Alekh Agarwal · Miro Dudik · John Langford · Damien Jose · Imed Zitouni -
2017 Poster: A-NICE-MC: Adversarial Training for MCMC »
Jiaming Song · Shengjia Zhao · Stefano Ermon -
2017 Poster: InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations »
Yunzhu Li · Jiaming Song · Stefano Ermon -
2017 Poster: Estimating Accuracy from Unlabeled Data: A Probabilistic Logic Approach »
Emmanouil Platanios · Hoifung Poon · Tom M Mitchell · Eric Horvitz -
2017 Poster: Neural Variational Inference and Learning in Undirected Graphical Models »
Volodymyr Kuleshov · Stefano Ermon -
2016 Poster: Solving Marginal MAP Problems with NP Oracles and Parity Constraints »
Yexiang Xue · zhiyuan li · Stefano Ermon · Carla Gomes · Bart Selman -
2016 Demonstration: Project Malmo - Minecraft for AI Research »
Katja Hofmann · Matthew A Johnson · Fernando Diaz · Alekh Agarwal · Tim Hutton · David Bignell · Evelyne Viegas -
2016 Poster: Efficient Second Order Online Learning by Sketching »
Haipeng Luo · Alekh Agarwal · Nicolò Cesa-Bianchi · John Langford -
2016 Poster: Contextual semibandits via supervised learning oracles »
Akshay Krishnamurthy · Alekh Agarwal · Miro Dudik -
2016 Poster: Generative Adversarial Imitation Learning »
Jonathan Ho · Stefano Ermon -
2016 Poster: Variational Bayes on Monte Carlo Steroids »
Aditya Grover · Stefano Ermon -
2016 Poster: Quantum Perceptron Models »
Ashish Kapoor · Nathan Wiebe · Krysta Svore -
2016 Poster: Adaptive Concentration Inequalities for Sequential Decision Problems »
Shengjia Zhao · Enze Zhou · Ashish Sabharwal · Stefano Ermon -
2016 Poster: PAC Reinforcement Learning with Rich Observations »
Akshay Krishnamurthy · Alekh Agarwal · John Langford -
2015 Workshop: Optimization for Machine Learning (OPT2015) »
Suvrit Sra · Alekh Agarwal · Leon Bottou · Sashank J. Reddi -
2015 Poster: Efficient and Parsimonious Agnostic Active Learning »
Tzu-Kuo Huang · Alekh Agarwal · Daniel Hsu · John Langford · Robert Schapire -
2015 Spotlight: Efficient and Parsimonious Agnostic Active Learning »
Tzu-Kuo Huang · Alekh Agarwal · Daniel Hsu · John Langford · Robert Schapire -
2015 Poster: Fast Convergence of Regularized Learning in Games »
Vasilis Syrgkanis · Alekh Agarwal · Haipeng Luo · Robert Schapire -
2015 Oral: Fast Convergence of Regularized Learning in Games »
Vasilis Syrgkanis · Alekh Agarwal · Haipeng Luo · Robert Schapire -
2014 Workshop: OPT2014: Optimization for Machine Learning »
Zaid Harchaoui · Suvrit Sra · Alekh Agarwal · Martin Jaggi · Miro Dudik · Aaditya Ramdas · Jean Lasserre · Yoshua Bengio · Amir Beck -
2014 Poster: Scalable Non-linear Learning with Adaptive Polynomial Expansions »
Alekh Agarwal · Alina Beygelzimer · Daniel Hsu · John Langford · Matus J Telgarsky -
2013 Workshop: Learning Faster From Easy Data »
Peter Grünwald · Wouter M Koolen · Sasha Rakhlin · Nati Srebro · Alekh Agarwal · Karthik Sridharan · Tim van Erven · Sebastien Bubeck -
2013 Workshop: OPT2013: Optimization for Machine Learning »
Suvrit Sra · Alekh Agarwal -
2013 Poster: Embed and Project: Discrete Sampling with Universal Hashing »
Stefano Ermon · Carla Gomes · Ashish Sabharwal · Bart Selman -
2012 Workshop: Optimization for Machine Learning »
Suvrit Sra · Alekh Agarwal -
2012 Poster: Patient Risk Stratification for Hospital-Associated C. Diff as a Time-Series Classification Task »
Jenna Wiens · John Guttag · Eric Horvitz -
2012 Poster: Multilabel Classification using Bayesian Compressed Sensing »
Ashish Kapoor · Raajay Viswanathan · Prateek Jain -
2012 Spotlight: Patient Risk Stratification for Hospital-Associated C. Diff as a Time-Series Classification Task »
Jenna Wiens · John Guttag · Eric Horvitz -
2012 Poster: Stochastic optimization and sparse statistical recovery: Optimal algorithms for high dimensions »
Alekh Agarwal · Sahand N Negahban · Martin J Wainwright -
2012 Poster: Density Propagation and Improved Bounds on the Partition Function »
Stefano Ermon · Carla Gomes · Ashish Sabharwal · Bart Selman -
2011 Workshop: Computational Trade-offs in Statistical Learning »
Alekh Agarwal · Sasha Rakhlin -
2011 Poster: Distributed Delayed Stochastic Optimization »
Alekh Agarwal · John Duchi -
2011 Poster: Stochastic convex optimization with bandit feedback »
Alekh Agarwal · Dean P Foster · Daniel Hsu · Sham M Kakade · Sasha Rakhlin -
2011 Poster: Accelerated Adaptive Markov Chain for Partition Function Computation »
Stefano Ermon · Carla Gomes · Ashish Sabharwal · Bart Selman -
2011 Spotlight: Accelerated Adaptive Markov Chain for Partition Function Computation »
Stefano Ermon · Carla Gomes · Ashish Sabharwal · Bart Selman -
2010 Workshop: Learning on Cores, Clusters, and Clouds »
Alekh Agarwal · Lawrence Cayton · Ofer Dekel · John Duchi · John Langford -
2010 Spotlight: Distributed Dual Averaging In Networks »
John Duchi · Alekh Agarwal · Martin J Wainwright -
2010 Poster: Distributed Dual Averaging In Networks »
John Duchi · Alekh Agarwal · Martin J Wainwright -
2010 Oral: Fast global convergence rates of gradient methods for high-dimensional statistical recovery »
Alekh Agarwal · Sahand N Negahban · Martin J Wainwright -
2010 Poster: Fast global convergence rates of gradient methods for high-dimensional statistical recovery »
Alekh Agarwal · Sahand N Negahban · Martin J Wainwright -
2009 Workshop: Analysis and Design of Algorithms for Interactive Machine Learning »
Sumit Basu · Ashish Kapoor -
2009 Poster: Information-theoretic lower bounds on the oracle complexity of convex optimization »
Alekh Agarwal · Peter Bartlett · Pradeep Ravikumar · Martin J Wainwright -
2009 Spotlight: Information-theoretic lower bounds on the oracle complexity of convex optimization »
Alekh Agarwal · Peter Bartlett · Pradeep Ravikumar · Martin J Wainwright -
2009 Poster: Breaking Boundaries Between Induction Time and Diagnosis Time Active Information Acquisition »
Ashish Kapoor · Eric Horvitz -
2007 Poster: An Analysis of Inference with the Universum »
Fabian H Sinz · Olivier Chapelle · Alekh Agarwal · Bernhard Schölkopf -
2007 Spotlight: An Analysis of Inference with the Universum »
Fabian H Sinz · Olivier Chapelle · Alekh Agarwal · Bernhard Schölkopf