A Distribution Optimization Framework for Confidence Bounds of Risk Measures
We present a distribution optimization framework that significantly improves confidence bounds for various risk measures compared to previous methods. Our framework encompasses popular risk measures such as the entropic risk measure, conditional value at risk (CVaR), spectral risk measure, distortion risk measure, equivalent certainty, and rank-dependent expected utility, which are well established in risk-sensitive decision-making literature. To achieve this, we introduce two estimation schemes based on concentration bounds derived from the empirical distribution, specifically using either the Wasserstein distance or the supremum distance. Unlike traditional approaches that add or subtract a confidence radius from the empirical risk measures, our proposed schemes evaluate a specific transformation of the empirical distribution based on the distance. Consequently, our confidence bounds consistently yield tighter results compared to previous methods. We further verify the efficacy of the proposed framework by providing tighter problem-dependent regret bound for the CVaR bandit.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingSimilar Papers 제목 키워드 기반
X-Armed Bandits: Optimizing Quantiles, CVaR and Other Risks
We propose and analyze StoROO, an algorithm for risk optimization on stochastic black-box functions derived from StoOO. Motivated by risk-averse decision making fields like agriculture, medicine, biology or finance, we d…
Decision MakingEstimation of discrete distributions in relative entropy, and the deviations of the missing mass
We study the problem of estimating a distribution over a finite alphabet from an i.i.d. sample, with accuracy measured in relative entropy (Kullback-Leibler divergence). While optimal expected risk bounds are known, high…
Sample-Based Bounds for Coherent Risk Measures: Applications to Policy Synthesis and Verification
The dramatic increase of autonomous systems subject to variable environments has given rise to the pressing need to consider risk in both the synthesis and verification of policies for these systems. This paper aims to a…
Capability Minimization as a Safety Primitive: Risk-Aware Causal Gating for Least-Privilege LLM Agents
Modern decision systems increasingly rely on learned components whose outputs may be confident yet wrong, exposing downstream actions to costly errors. We introduce Risk-Aware Causal Gating (RACG), a framework that decid…
How Catastrophic is Your LLM? Certifying Risk in Conversation
Large Language Models (LLMs) can produce catastrophic responses in conversational settings that pose serious risks to public safety and security. Existing evaluations often fail to fully reveal these vulnerabilities beca…
Semantic Similarity