This work characterize the optimal policy under known distributions, and shows that it reduces to a prediction set-based solution for the CVaR, which provides an operational interpretation of conformal prediction-type prediction sets.
Abstract
We study risk-averse decision making, in which an agent selects actions while being uncertain about the true system state. The risk is measured via optimized certainty equivalent (OCE) metrics, which generalize popular criteria such as mean-variance risk and conditional value-at-risk (CVaR). We characterize the optimal policy under known distributions, and show that it reduces to a prediction set-based solution for the CVaR. This provides an operational interpretation of conformal prediction-type prediction sets. For unknown distributions, we develop a data-driven calibration strategy, based on a synthetic model for the likelihood and held-out calibration data, yielding high-probability control of the OCE risk. The approach is evaluated on two wireless beamforming settings.
The problem of maximizing the weighted average of performance certificates in the presence of uncertainty about the true system state is shown to be equivalent to an optimization over nested prediction sets, connecting to the literature on conformal prediction and extending prior art on single-level risk-averse decisio...
The new modeling paradigm subsumes several classical SOC/MDP formulations, including risk-averse and distributionally robust SOC/MDPs as well as partially observed and Bayes-adaptive MDPs, and generates so-called preference robust SOC/MDP models.
Quantum measurements are conventionally optimized to maximize the average of a utility that depends on the true state and on the measurement outcome. However, when the outcome of the measurement is used as an action within a larger decision-making system, the average utility does not capture the risk of poor outcomes....
This work argues that, in the presence of a simulation model, natural attempts to integrate variance reduction into optimization, even executed in a reasonable adaptive fashion, encounter fundamental challenges in guaranteeing realistic runtime when using common stochastic gradient descent algorithms.
RATTL targets runtime safety for agents, including LLM-based systems, acting under uncertainty, and proves a Safety Sandwich: the RATTL value lies between the uninformed robust value and the full- knowledge optimum, with a gap that vanishes as the posterior concentrates.
This work builds a score-calibrated robustness framework that converts any fixed point predictor into a decision-relevant uncertainty representation through distribution-free conformal calibration, and shows that conformal scores endow fixed black-box predictors with an interpretable uncertainty scale for downstream de...
![Director of Machine Learning Insights [Part 4]](/uploads/articles/4d4046d553c83e57a3aa9af0665a2d2d482ad7c9.png)