Timezone: »
On counterfactual inference with unobserved confounding
Abhin Shah · Raaz Dwivedi · Devavrat Shah · Gregory Wornell
Event URL: https://openreview.net/forum?id=e9NQvYNUOAl »
Given an observational study with $n$ independent but heterogeneous units and one $p$-dimensional sample per unit containing covariates, interventions, and outcomes, our goal is to learn counterfactual distribution for each unit. We consider studies with unobserved confounding which introduces statistical biases between interventions and outcomes as well as exacerbates the heterogeneity across units. Modeling the underlying joint distribution as an exponential family and under suitable conditions, we reduce learning the $n$ unit-level counterfactual distributions to learning $n$ exponential family distributions with heterogeneous parameters and only one sample per distribution. We introduce a convex objective that pools all $n$ samples to jointly learn all $n$ parameters and provide a unit-wise mean squared error bound that scales linearly with the metric entropy of the parameter space. For example, when the parameters are $s$-sparse linear combination of $k$ known vectors, the error is $O(s\log k/p)$. En route, we derive sufficient conditions for compactly supported distributions to satisfy the logarithmic Sobolev inequality.
Given an observational study with $n$ independent but heterogeneous units and one $p$-dimensional sample per unit containing covariates, interventions, and outcomes, our goal is to learn counterfactual distribution for each unit. We consider studies with unobserved confounding which introduces statistical biases between interventions and outcomes as well as exacerbates the heterogeneity across units. Modeling the underlying joint distribution as an exponential family and under suitable conditions, we reduce learning the $n$ unit-level counterfactual distributions to learning $n$ exponential family distributions with heterogeneous parameters and only one sample per distribution. We introduce a convex objective that pools all $n$ samples to jointly learn all $n$ parameters and provide a unit-wise mean squared error bound that scales linearly with the metric entropy of the parameter space. For example, when the parameters are $s$-sparse linear combination of $k$ known vectors, the error is $O(s\log k/p)$. En route, we derive sufficient conditions for compactly supported distributions to satisfy the logarithmic Sobolev inequality.
Author Information
Abhin Shah (MIT)
Raaz Dwivedi (Harvard University)
Devavrat Shah (Massachusetts Institute of Technology)
Devavrat Shah is a professor of Electrical Engineering & Computer Science and Director of Statistics and Data Science at MIT. He received PhD in Computer Science from Stanford. He received Erlang Prize from Applied Probability Society of INFORMS in 2010 and NeuIPS best paper award in 2008.
Gregory Wornell (MIT)
More from the Same Authors
-
2021 Spotlight: Regulating algorithmic filtering on social media »
Sarah Cen · Devavrat Shah -
2021 : Regret, stability, and fairness in matching markets with bandit learners »
Sarah Cen · Devavrat Shah -
2021 : Regret, stability, and fairness in matching markets with bandit learners »
Sarah Cen · Devavrat Shah -
2022 : A Causal Inference Framework for Network Interference with Panel Data »
Sarah Cen · Anish Agarwal · Christina Yu · Devavrat Shah -
2023 Poster: Front-door Adjustment Beyond Markov Equivalence with Limited Graph Knowledge »
Abhin Shah · Karthikeyan Shanmugam · Murat Kocaoglu -
2023 Poster: Auditing for Human Expertise »
Rohan Alur · Loren Laine · Darrick Li · Manish Raghavan · Devavrat Shah · Dennis Shung -
2023 Poster: Score-based Source Separation with Applications to Digital Communication Signals »
Tejas Jayashankar · Gary C.F. Lee · Alejandro Lancho · Amir Weiss · Yury Polyanskiy · Gregory Wornell -
2023 Poster: SAMoSSA: Multivariate Singular Spectrum Analysis with Stochastic Autoregressive Noise »
Abdullah Alomar · Munther Dahleh · Sean Mann · Devavrat Shah -
2021 Poster: A Computationally Efficient Method for Learning Exponential Family Distributions »
Abhin Shah · Devavrat Shah · Gregory Wornell -
2021 Poster: Regulating algorithmic filtering on social media »
Sarah Cen · Devavrat Shah -
2021 Poster: Change Point Detection via Multivariate Singular Spectrum Analysis »
Arwa Alanqary · Abdullah Alomar · Devavrat Shah -
2021 Poster: An Exact Characterization of the Generalization Error for the Gibbs Algorithm »
Gholamali Aminian · Yuheng Bu · Laura Toni · Miguel Rodrigues · Gregory Wornell -
2021 Poster: PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators »
Anish Agarwal · Abdullah Alomar · Varkey Alumootil · Devavrat Shah · Dennis Shen · Zhi Xu · Cindy Yang -
2020 Poster: Estimation of Skill Distribution from a Tournament »
Ali Jadbabaie · Anuran Makur · Devavrat Shah -
2020 Spotlight: Estimation of Skill Distribution from a Tournament »
Ali Jadbabaie · Anuran Makur · Devavrat Shah -
2020 Poster: Sample Efficient Reinforcement Learning via Low-Rank Matrix Estimation »
Devavrat Shah · Dogyoon Song · Zhi Xu · Yuzhe Yang -
2020 Demonstration: tspDB: Time Series Predict DB »
Anish Agarwal · Abdullah Alomar · Devavrat Shah -
2019 Poster: On Robustness of Principal Component Regression »
Anish Agarwal · Devavrat Shah · Dennis Shen · Dogyoon Song -
2019 Poster: Computational Mirrors: Blind Inverse Light Transport by Deep Matrix Factorization »
Miika Aittala · Prafull Sharma · Lukas Murmann · Adam Yedidia · Gregory Wornell · Bill Freeman · Fredo Durand -
2019 Oral: On Robustness of Principal Component Regression »
Anish Agarwal · Devavrat Shah · Dennis Shen · Dogyoon Song -
2019 Poster: Learning New Tricks From Old Dogs: Multi-Source Transfer Learning From Pre-Trained Networks »
Joshua Lee · Prasanna Sattigeri · Gregory Wornell -
2019 Tutorial: Synthetic Control »
Alberto Abadie · Vishal Misra · Devavrat Shah -
2018 Poster: Q-learning with Nearest Neighbors »
Devavrat Shah · Qiaomin Xie -
2018 Poster: Co-regularized Alignment for Unsupervised Domain Adaptation »
Abhishek Kumar · Prasanna Sattigeri · Kahini Wadhawan · Leonid Karlinsky · Rogerio Feris · Bill Freeman · Gregory Wornell -
2017 Workshop: Nearest Neighbors for Modern Applications with Massive Data: An Age-old Solution with New Challenges »
George H Chen · Devavrat Shah · Christina Lee -
2017 Poster: Thy Friend is My Friend: Iterative Collaborative Filtering for Sparse Matrix Estimation »
Christian Borgs · Jennifer Chayes · Christina Lee · Devavrat Shah -
2016 Poster: Blind Regression: Nonparametric Regression for Latent Variable Models via Collaborative Filtering »
Dogyoon Song · Christina Lee · Yihua Li · Devavrat Shah -
2014 Workshop: Analysis of Rank Data: Confluence of Social Choice, Operations Research, and Machine Learning »
Shivani Agarwal · Hossein Azari Soufiani · Guy Bresler · Sewoong Oh · David Parkes · Arun Rajkumar · Devavrat Shah -
2014 Poster: Hardness of parameter estimation in graphical models »
Guy Bresler · David Gamarnik · Devavrat Shah -
2014 Poster: A Latent Source Model for Online Collaborative Filtering »
Guy Bresler · George H Chen · Devavrat Shah -
2014 Spotlight: A Latent Source Model for Online Collaborative Filtering »
Guy Bresler · George H Chen · Devavrat Shah -
2014 Poster: Learning Mixed Multinomial Logit Model from Ordinal Data »
Sewoong Oh · Devavrat Shah -
2014 Poster: Structure learning of antiferromagnetic Ising models »
Guy Bresler · David Gamarnik · Devavrat Shah -
2013 Workshop: Crowdsourcing: Theory, Algorithms and Applications »
Jennifer Wortman Vaughan · Greg Stoddard · Chien-Ju Ho · Adish Singla · Michael Bernstein · Devavrat Shah · Arpita Ghosh · Evgeniy Gabrilovich · Denny Zhou · Nikhil Devanur · Xi Chen · Alexander Ihler · Qiang Liu · Genevieve Patterson · Ashwinkumar Badanidiyuru Varadaraja · Hossein Azari Soufiani · Jacob Whitehill -
2013 Poster: A Latent Source Model for Nonparametric Time Series Classification »
George H Chen · Stanislav Nikolov · Devavrat Shah -
2013 Poster: Computing the Stationary Distribution Locally »
Christina Lee · Asuman Ozdaglar · Devavrat Shah -
2012 Poster: Iterative ranking from pair-wise comparisons »
Sahand N Negahban · Sewoong Oh · Devavrat Shah -
2012 Spotlight: Iterative ranking from pair-wise comparisons »
Sahand N Negahban · Sewoong Oh · Devavrat Shah -
2011 Poster: Iterative Learning for Reliable Crowdsourcing Systems »
David R Karger · Sewoong Oh · Devavrat Shah -
2011 Oral: Iterative Learning for Reliable Crowdsourcing Systems »
David R Karger · Sewoong Oh · Devavrat Shah -
2009 Poster: A Data-Driven Approach to Modeling Choice »
Vivek Farias · Srikanth Jagabathula · Devavrat Shah -
2009 Spotlight: A Data-Driven Approach to Modeling Choice »
Vivek Farias · Srikanth Jagabathula · Devavrat Shah -
2009 Poster: Local Rules for Global MAP: When Do They Work ? »
Kyomin Jung · Pushmeet Kohli · Devavrat Shah -
2008 Poster: Inferring rankings under constrained sensing »
Srikanth Jagabathula · Devavrat Shah -
2008 Oral: Inferring rankings under constrained sensing »
Srikanth Jagabathula · Devavrat Shah -
2007 Spotlight: Message Passing for Max-weight Independent Set »
Sujay Sanghavi · Devavrat Shah · Alan S Willsky -
2007 Poster: Message Passing for Max-weight Independent Set »
Sujay Sanghavi · Devavrat Shah · Alan S Willsky -
2007 Poster: Local Algorithms for Approximate Inference in Minor-Excluded Graphs »
Kyomin Jung · Devavrat Shah