Timezone: »

 
Poster
Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning
Aurelien Bibaut · Nathan Kallus · Maria Dimakopoulou · Antoine Chambaz · Mark van der Laan

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @
in Poster Session 6 »

Empirical risk minimization (ERM) is the workhorse of machine learning, whether for classification and regression or for off-policy policy learning, but its model-agnostic guarantees can fail when we use adaptively collected data, such as the result of running a contextual bandit algorithm. We study a generic importance sampling weighted ERM algorithm for using adaptively collected data to minimize the average of a loss function over a hypothesis class and provide first-of-their-kind generalization guarantees and fast convergence rates. Our results are based on a new maximal inequality that carefully leverages the importance sampling structure to obtain rates with the good dependence on the exploration rate in the data. For regression, we provide fast rates that leverage the strong convexity of squared-error loss. For policy learning, we provide regret guarantees that close an open gap in the existing literature whenever exploration decays to zero, as is the case for bandit-collected data. An empirical investigation validates our theory.

Keywords: Theory · Reinforcement Learning and Planning · Machine Learning · Bandits

Author Information

Aurelien Bibaut (Netflix)
Nathan Kallus (Cornell University)
Maria Dimakopoulou (Stanford University)
Antoine Chambaz (Université de Paris)
Mark van der Laan

More from the Same Authors