Oral
Bayesian Counterfactual Risk Minimization
Ben London · Ted Sandler

Tue Jun 11th 04:25 -- 04:30 PM @ Room 104

We present a Bayesian view of counterfactual risk minimization (CRM), also known as offline policy optimization from logged bandit feedback. Using PAC-Bayesian analysis, we derive a new generalization bound for the truncated IPS estimator. We apply the bound to a class of Bayesian policies, which motivates a novel, potentially data-dependent, regularization technique for CRM. Experimental results indicate that this technique outperforms standard $L_2$ regularization, and that it is competitive with variance regularization while being both simpler to implement and more computationally efficient.

Author Information

Ben London (Amazon)
Ted Sandler (Amazon.com)

Related Events (a corresponding poster, oral, or spotlight)