Unconstrained Robust Online Convex Optimization
Keywords: online learning, online convex optimization, adversarial corruption, comparator adaptive, parameter-free, unconstrained domain
TL;DR: "This paper addresses online learning with ''corrupted'' feedback in unconstrained domain."
Abstract: This paper addresses online learning with ''corrupted'' feedback. Our learner is provided with potentially corrupted gradients $\tilde g_t$ instead of the ''true'' gradients $g_t$. We make no assumptions about how the corruptions arise: they could be the result of outliers, mislabeled data, or even malicious interference. We focus on the difficult ''unconstrained'' setting in which our algorithm must maintain low regret with respect to any comparison point $\||u\|| \in \mathbb{R}^d$. Perhaps surprisingly, the unconstrained setting is significantly more challenging as existing algorithms suffer extremely high regret even with very tiny amounts of corruption (which is not true in the case of a bounded domain). Our algorithms guarantee regret $ \||u\||G (\sqrt{T} + k) $ when Lipschitz constant $G \ge \max_t \||g_t\||$ is known, where $k$ is a measure of the total amount of corruption. When $G$ is unknown and incur an extra additive penalty of $(\||u\||^2+G^2) k$.
Primary Area: optimization
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 5035
Loading