An Online Newton's Method for Time-varying Linear Equality Constraints
Abstract
We consider online optimization problems with time-varying linear equality constraints. In this framework, an agent makes sequential decisions using only prior information. At every round, the agent suffers an environment-determined loss and must satisfy time-varying constraints. Both the loss functions and the constraints can be chosen adversarially. We propose the Online Projected Equality-constrained Newton Method (OPEN-M) to tackle this family of problems. We obtain sublinear dynamic regret and constraint violation bounds for OPEN-M under mild conditions. Namely, smoothness of the loss function and boundedness of the inverse Hessian at the optimum are required, but not convexity. Finally, we show OPEN-M outperforms state-of-the-art online constrained optimization algorithms in a numerical network flow application.
Cite
@article{arxiv.2212.02748,
title = {An Online Newton's Method for Time-varying Linear Equality Constraints},
author = {Jean-Luc Lupien and Antoine Lesage-Landry},
journal= {arXiv preprint arXiv:2212.02748},
year = {2023}
}
Comments
Version corrects small typos from the previous versions. Formatting is done in color in the style of IEEE