Timezone: »
Poster
Accurate Inference for Adaptive Linear Models
Yash Deshpande · Lester Mackey · Vasilis Syrgkanis · Matt Taddy
Estimators computed from adaptively collected data do not behave like their non-adaptive brethren. Rather, the sequential dependence of the collection policy can lead to severe distributional biases that persist even in the infinite data limit. We develop a general method -- \emph{$\vect{W}$-decorrelation} -- for transforming the bias of adaptive linear regression estimators into variance. The method uses only coarse-grained information about the data collection policy and does not need access to propensity scores or exact knowledge of the policy. We bound the finite-sample bias and variance of the $\vect{W}$-estimator and develop asymptotically correct confidence intervals based on a novel martingale central limit theorem. We then demonstrate the empirical benefits of the generic $\vect{W}$-decorrelation procedure in two different adaptive data settings: the multi-armed bandit and the autoregressive time series.
Author Information
Yash Deshpande (Massachusetts Institute of Technology)
Lester Mackey (Microsoft Research)
Vasilis Syrgkanis (Microsoft Research)
Matt Taddy (MICROSOFT)
Related Events (a corresponding poster, oral, or spotlight)
-
2018 Oral: Accurate Inference for Adaptive Linear Models »
Fri. Jul 13th 03:40 -- 03:50 PM Room A5
More from the Same Authors
-
2020 : Contributed Talk: Incentivizing Bandit Exploration:Recommendations as Instruments »
Dung Ngo · Logan Stapleton · Vasilis Syrgkanis · Steven Wu -
2021 : SNoB: Social Norm Bias of “Fair” Algorithms »
Myra Cheng · Maria De-Arteaga · Lester Mackey · Adam Tauman Kalai -
2021 : Are You Man Enough? Even Fair Algorithms Conform to Societal Norms »
Myra Cheng · Maria De-Arteaga · Lester Mackey · Adam Tauman Kalai -
2021 : DoWhy: Addressing Challenges in Expressing and Validating Causal Assumptions »
Amit Sharma · Vasilis Syrgkanis · cheng zhang · Emre Kiciman -
2022 : Adversarial Estimation of Riesz Representers »
Victor Chernozhukov · Whitney Newey · Rahul Singh · Vasilis Syrgkanis -
2023 : Adaptive Bias Correction for Improved Subseasonal Forecasting »
Soukayna Mouatadid · Paulo Orenstein · Genevieve Flaspohler · Judah Cohen · Miruna Oprescu · Ernest Fraenkel · Lester Mackey -
2022 Poster: RieszNet and ForestRiesz: Automatic Debiased Machine Learning with Neural Nets and Random Forests »
Victor Chernozhukov · Whitney Newey · Víctor Quintas-Martínez · Vasilis Syrgkanis -
2022 Oral: RieszNet and ForestRiesz: Automatic Debiased Machine Learning with Neural Nets and Random Forests »
Victor Chernozhukov · Whitney Newey · Víctor Quintas-Martínez · Vasilis Syrgkanis -
2022 Poster: Scalable Spike-and-Slab »
Niloy Biswas · Lester Mackey · Xiao-Li Meng -
2022 Spotlight: Scalable Spike-and-Slab »
Niloy Biswas · Lester Mackey · Xiao-Li Meng -
2021 : Lester Mackey: Online Learning with Optimism and Delay »
Lester Mackey -
2021 Poster: Incentivizing Compliance with Algorithmic Instruments »
Dung Ngo · Logan Stapleton · Vasilis Syrgkanis · Steven Wu -
2021 Spotlight: Incentivizing Compliance with Algorithmic Instruments »
Dung Ngo · Logan Stapleton · Vasilis Syrgkanis · Steven Wu -
2019 Workshop: Stein’s Method for Machine Learning and Statistics »
Francois-Xavier Briol · Lester Mackey · Chris Oates · Qiang Liu · Larry Goldstein · Larry Goldstein -
2019 Poster: Orthogonal Random Forest for Causal Inference »
Miruna Oprescu · Vasilis Syrgkanis · Steven Wu -
2019 Oral: Orthogonal Random Forest for Causal Inference »
Miruna Oprescu · Vasilis Syrgkanis · Steven Wu -
2019 Poster: Stein Point Markov Chain Monte Carlo »
Wilson Ye Chen · Alessandro Barp · Francois-Xavier Briol · Jackson Gorham · Mark Girolami · Lester Mackey · Chris Oates -
2019 Oral: Stein Point Markov Chain Monte Carlo »
Wilson Ye Chen · Alessandro Barp · Francois-Xavier Briol · Jackson Gorham · Mark Girolami · Lester Mackey · Chris Oates -
2018 Poster: Semiparametric Contextual Bandits »
Akshay Krishnamurthy · Steven Wu · Vasilis Syrgkanis -
2018 Poster: Stein Points »
Wilson Ye Chen · Lester Mackey · Jackson Gorham · Francois-Xavier Briol · Chris J Oates -
2018 Poster: Orthogonal Machine Learning: Power and Limitations »
Ilias Zadik · Lester Mackey · Vasilis Syrgkanis -
2018 Oral: Stein Points »
Wilson Ye Chen · Lester Mackey · Jackson Gorham · Francois-Xavier Briol · Chris J Oates -
2018 Oral: Orthogonal Machine Learning: Power and Limitations »
Ilias Zadik · Lester Mackey · Vasilis Syrgkanis -
2018 Oral: Semiparametric Contextual Bandits »
Akshay Krishnamurthy · Steven Wu · Vasilis Syrgkanis -
2017 Poster: Deep IV: A Flexible Approach for Counterfactual Prediction »
Jason Hartford · Greg Lewis · Kevin Leyton-Brown · Matt Taddy -
2017 Talk: Deep IV: A Flexible Approach for Counterfactual Prediction »
Jason Hartford · Greg Lewis · Kevin Leyton-Brown · Matt Taddy