DeLTA seminar by Niklas Pfister
On 25 October, the DeLTA Lab from the Department of Computer Science, University of Copenhagen, holds a seminar titled 'Statistical Testing under Distributional Shifts: Applications in Offline Contextual Bandits' by Niklas Pfister.
Niklas Pfister, MATH department, University of Copenhagen
Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote
Testing hypotheses about the behavior of an unobserved policy in offline contextual bandits is a challenging task because no data from the distribution of interest is available. In this talk, we will introduce a general framework for statistical testing in such settings. Formally, our framework for statistical testing under distributional shifts aims to test a target hypothesis "P in H0'' using observed data from a distribution Q, where we assume that P is related to Q through a known distributional shift. We propose a general testing procedure that first resamples from the observed data to construct an auxiliary data set (mimicking properties of P) and then applies an existing test in the target domain. We prove that this procedure holds pointwise asymptotic level if the target test holds pointwise asymptotic level, the size of the resample is at most of order square root n, and the resampling weights are well-behaved.
The talk is based on joint work with Nikolaj Thams, Sorawit Saengkyongam and Jonas Peters.
Other Upcoming DeLTA seminars:
15 November 2021 @ 10:00. Sorawit Saengkyongam. Invariant Policy Learning: A Causal Perspective.
You can subscribe to DeLTA Seminar mailing list by sending an empty email to email@example.com.
Information about DeLTA Seminars is available at the DeLTA Lab page: https://sites.google.com/diku.edu/delta
DeLTA is a research group affiliated with the Department of Computer Science at the University of Copenhagen studying diverse aspects of Machine Learning Theory and its applications, including, but not limited to Reinforcement Learning, Online Learning and Bandits, PAC-Bayesian analysis