Gradient Equilibrium in Online Learning: Theory and Applications

AN Angelopoulos, MI Jordan, RJ Tibshirani - arxiv preprint arxiv …, 2025 - arxiv.org
We present a new perspective on online learning that we refer to as gradient equilibrium: a
sequence of iterates achieves gradient equilibrium if the average of gradients of losses …

Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents

S Kiyani, G Pappas, A Roth, H Hassani - arxiv preprint arxiv:2502.02561, 2025 - arxiv.org
A fundamental question in data-driven decision making is how to quantify the uncertainty of
predictions in ways that can usefully inform downstream action. This interface between …

Distributed Conformal Prediction via Message Passing

H Wen, H **ng, O Simeone - arxiv preprint arxiv:2501.14544, 2025 - arxiv.org
Post-hoc calibration of pre-trained models is critical for ensuring reliable inference,
especially in safety-critical domains such as healthcare. Conformal Prediction (CP) offers a …

Robust Bayesian Optimization via Localized Online Conformal Prediction

D Kim, M Zecchin, S Park, J Kang… - arxiv preprint arxiv …, 2024 - arxiv.org
Bayesian optimization (BO) is a sequential approach for optimizing black-box objective
functions using zeroth-order noisy observations. In BO, Gaussian processes (GPs) are …