Instantiating Bayesian CVaR lower bounds in Interactive Decision Making Problems
Provides a practical tool for deriving risk-sensitive lower bounds in interactive learning, but is incremental as it applies an existing framework to new examples.
This paper instantiates a generalized-Fano framework for lower bounding Bayesian CVaR in interactive decision making, deriving explicit bounds for problems like Gaussian bandits that clarify parameter dependencies.
Recent work established a generalized-Fano framework for lower bounding prior-predictive (Bayesian) CVaR in interactive statistical decision making. In this paper, we show how to instantiate that framework in concrete interactive problems and derive explicit Bayesian CVaR lower bounds from its abstract corollaries. Our approach compares a hard model with a reference model using squared Hellinger distance, and combines a lower bound on a reference hinge term with a bound on the distinguishability of the two models. We apply this approach to canonical examples, including Gaussian bandits, and obtain explicit bounds that make the dependence on key problem parameters transparent. These results show how the generalized-Fano Bayesian CVaR framework can be used as a practical lower-bound tool for interactive learning and risk-sensitive decision making.