Correlation uncertainty: a decision-theoretic approach
We provide a decision-theoretic foundation for uncertainty about the correlation structure on a Cartesian product of probability spaces. Our contribution is two-fold: we first provide a full characterization of the set of possible correlations between subspaces as a convex polytope. Its extreme points are identified as the local maxima of mutual information and as maximally zero probability measures. Second, we derive an axiomatic characterization of preferences narrowing down the set of correlations a decision maker considers, making behavior about correlation testable. Thereby, she may regard collections of subspaces as independent from one another. We illustrate our model and results in simple examples on climate change, insurance and portfolio choice.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
False Correlation Reduction for Offline Reinforcement Learning
Offline reinforcement learning (RL) harnesses the power of massive datasets for resolving sequential decision problems. Most existing papers only discuss defending against out-of-distribution (OOD) actions while we inves…
D4RLDecision MakingOffline RLreinforcement-learning+2Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning
Current evaluation of epistemic uncertainty relies on tasks such as out-ofdistribution detection and active learning. However, the Bayes-optimal decision strategies for these tasks do not coincide with the scores commonl…
Active LearningSeeing is not Believing: Robust Reinforcement Learning against Spurious Correlation
Robustness has been extensively studied in reinforcement learning (RL) to handle various forms of uncertainty such as random perturbations, rare events, and malicious attacks. In this work, we consider one critical type …
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Stable Adversarial Learning under Distributional Shifts
Machine learning algorithms with empirical risk minimization are vulnerable under distributional shifts due to the greedy adoption of all the correlations found in training data. Recently, there are robust learning metho…
A decision-theoretic approach to dealing with uncertainty in quantum mechanics
We provide a decision-theoretic framework for dealing with uncertainty in quantum mechanics. This uncertainty is two-fold: on the one hand there may be uncertainty about the state the quantum system is in, and on the oth…