The paper introduces a method for risk‑averse machine learning that uses credal sets—collections of probability distributions—to capture epistemic uncertainty about the true loss distribution. By producing predictions as credal sets and applying a novel decision rule that selects a single predictive distribution for conditional value‑at‑risk (CVaR) minimization, the approach aims to reliably avoid catastrophic decisions across classification, distribution shift, and reinforcement learning scenarios while maintaining near‑optimal expected performance.
arXiv:2602. 08470v3 Announce Type: replace Abstract: Credal predictors are models that are aware of epistemic uncertainty and produce a convex set of probabilistic predictions.
arXiv:2607. 14407v1 Announce Type: cross Abstract: Many signal processing systems ultimately exist to {act}.
arXiv:2405.14749v3 Announce Type: replace-cross Abstract: Risk-sensitive reinforcement learning (RL) is crucial for maintaining reliable performance in high-stakes applications. While traditional RL...
arXiv:2606. 05551v1 Announce Type: cross Abstract: Reliable decision making pipelines powered by machine learning models require uncertainty quantification (UQ) methods that come with explicit safety guarantees.
The paper addresses the challenge of creating machine learning learners that can guarantee provably correct predictions in difficult test-time scenarios, such as adversarial attacks and natural distribution shifts. It introduces a reliable learner with optimal theoretical guarantees for these settings and discusses practical implementations. The authors demonstrate strong performance on examples like linear separators under log-concave distributions and smooth boundary classifiers under smooth probability distributions.
arXiv:2610.27214v1 Announce Type: new Abstract: Estimating extreme risk in reinforcement learning becomes increasingly difficult as the confidence level increases, since only a small number of observ...
arXiv:2607. 14817v1 Announce Type: cross Abstract: Current evaluation of epistemic uncertainty relies on tasks such as out-ofdistribution detection and active learning.
arXiv:2607. 02206v1 Announce Type: cross Abstract: Predictions are increasingly used to guide high-stakes decisions, from treatment selection to policy making.
The paper introduces the concept of observational multiplicity, where multiple probabilistic classifiers can perform similarly yet produce conflicting predictions, undermining interpretability and safety. It proposes measuring this arbitrariness through a regret metric that captures how predictions could shift with different training labels. The authors present a general method to estimate regret, show it varies across dataset groups, and discuss its use for safety via abstention and targeted data collection.
arXiv:2609. 10866v1 Announce Type: new Abstract: Reinforcement learning (RL) agents deployed in real-world environments are often vulnerable to adversarial perturbations in state observations, creating risks in safety-critical applications.
arXiv:2505. 19033v2 Announce Type: replace-cross Abstract: Conformal prediction (CP) is a widely used frequentist framework to quantify uncertainty by constructing prediction sets with user-specified marginal coverage guarantees.
arXiv:2607. 02755v1 Announce Type: cross Abstract: Training AIs to be risk-averse in resources could offer a failsafe in the event that AIs turn out misaligned.