On the Statistical Complexity of Batch Learning: Theory and Algorithms

Abstract

In this work we develop the technique of optimism regularization, a simple way of inducing optimistic predictions in NN models. I show this simple technique, inspired by the theoretical requirement of optimism handily beats non-optimistic exploration strategies in the setting of genetic perturbation experiments, and other practical online data acquisition problems. We show how to use these methodologies to introduce algorithms for batch learning in the presence of NN function approximators. We also characterize the complexity of batch learning using the Eluder dimension

Date
Nov 1, 2022 12:00 AM
Event
AIMS Seminar
Location
Oxford University
Avatar
Aldo Pacchiano
Eric and Wendy Schmidt Center Fellow / Faculty

My research interests include online learning, Reinforcement Learning, Deep RL and Fairness.