Multiply Robust Off-policy Evaluation and Learning under Truncation by Death
Jul 24, 2023
Speakers
About
Typical off-policy evaluation (OPE) and off-policy learning (OPL) are not well-defined problems under "truncation by death", where the outcome of interest is not defined after some events, such as death. The standard OPE no longer yields consistent estimators, and the standard OPL results in sub-optimal policies. In this paper, we formulate OPE and OPL using principal stratification under "truncation by death". We propose a survivor value function for a subpopulation whose outcomes are always defined regardless of treatment conditions. We establish a novel identification strategy under principal ignorability, and derive the semiparametric efficiency bound of an OPE estimator. Then, we propose multiply robust estimators for OPE and OPL. We show that the proposed estimators are consistent and asymptotically normal even with flexible semi/nonparametric models for nuisance functions approximation. Moreover, under mild rate conditions of nuisance functions approximation, the estimators achieve the semiparametric efficiency bound. Finally, we conduct experiments to demonstrate the empirical performance of the proposed estimators.Typical off-policy evaluation (OPE) and off-policy learning (OPL) are not well-defined problems under "truncation by death", where the outcome of interest is not defined after some events, such as death. The standard OPE no longer yields consistent estimators, and the standard OPL results in sub-optimal policies. In this paper, we formulate OPE and OPL using principal stratification under "truncation by death". We propose a survivor value function for a subpopulation whose outcomes are always de…
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies
Zhlédnout později
Gati Aher, …
Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability
Zhlédnout později
Yitan Wang, …
Adversarial Cheap Talk
Zhlédnout později
Chris Lu, …
Fair Densities via Boosting the Sufficient Statistics of Exponential Families
Zhlédnout později
Understanding Social Reasoning in Language Models with Language Models
Zhlédnout později
Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time
Zhlédnout později
Zichang Liu, …