When modifying existing policies in high-risk settings, it is often necessary to ensure with high certainty that the newly proposed policy improves upon a baseline, such as the status quo. In this work, we consider the problem of safe policy improvement, where one only adopts a new policy if it is deemed to be better than the specified baseline with at least pre-specified probability. We focus on threshold policies, a ubiquitous class of policies with applications in economics, healthcare, and digital advertising. Existing methods rely on potentially underpowered safety checks and limit the opportunities for finding safe improvements, so too often they must revert to the baseline to maintain safety. We overcome these issues by leveraging the most powerful safety test in the asymptotic regime and allowing for multiple candidates to be tested for improvement over the baseline. We show that in adversarial settings, our approach controls the rate of adopting a policy worse than the baseline to the pre-specified error level, even in moderate sample sizes. We present CSPI and CSPI-MT, two novel heuristics for selecting cutoff(s) to maximize the policy improvement from baseline. We demonstrate through both synthetic and external datasets that our approaches improve both the detection rates of safe policies and the realized improvement, particularly under stringent safety requirements and low signal-to-noise conditions.
Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs
Department of Computer Science, Technion IIT(计算机科学系);Department of Statistics, University of Oxford(统计系);Department of Electrical and Computer Engineering, Technion IIT(电气与计算机工程系)
Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays
Department of Economics University of Wisconsin–Madison(经济学系威斯康星大学麦迪逊分校);Department of Finance University of Wisconsin–Madison(金融系威斯康星大学麦迪逊分校);Department of Computer Sciences University of Wisconsin–Madison(计算机科学系威斯康星大学麦迪逊分校)