arXiv:2610. 32339v1 Announce Type: cross Abstract: We determine the optimal regret in agnostic multiclass online learning with arbitrary, possibly infinite, label spaces.
arXiv:2609.21445v1 Announce Type: new Abstract: We prove that the optimal expected mistake bound of online learning a function class $\mathcal{H}$ by a randomized proper learning algorithm is $O(\mat...
arXiv:2609.38375v1 Announce Type: new Abstract: Can a constant number of linear minimizations per round improve on the $T^{3/4}$ regret rate of online Frank-Wolfe on general convex sets? Weibel et al...
arXiv:2602. 06257v2 Announce Type: replace Abstract: Online strategic classification studies settings in which agents strategically modify their features to obtain favorable predictions.
arXiv:2610. 11074v1 Announce Type: new Abstract: We establish near-optimal regret bounds for budget-constrained online learning against arbitrary classes of budget-pacing experts in the adversarial setting.
arXiv:2609. 29694v2 Announce Type: replace Abstract: How much does high confidence cost when a multiclass learner sees only whether its prediction is correct?
The paper introduces the concept of no‑regret language generation, requiring a generator to make a sublinear number of mistakes across all demonstration sequences and compatible target languages. It presents both a realizable and an agnostic variant, using tree‑based mistake‑forcing dimensions to characterize finite‑horizon minimax complexity and establish necessary and sufficient conditions for no‑regret generation. The authors also connect generation complexity to online prediction, providing optimal mistake bounds for language classes with finite Littlestone dimension.
arXiv:2611.05133v2 Announce Type: replace Abstract: We study PAC learning when each example comes with a set of at most $\ell$ correct labels and a prediction is correct if it belongs to this set. Tr...
arXiv:2504.09006v5 Announce Type: replace-cross Abstract: We initiate the study of structured Stackelberg games, a novel form of strategic interaction between a leader and a follower where contextual...
arXiv:2608. 29503v1 Announce Type: new Abstract: Worst-case online classification is governed by sequential complexity, such as Littlestone dimension, and can be impossible even for statistically simple classes, such as thresholds of VC dimension one.
arXiv:2608. 25182v1 Announce Type: cross Abstract: In this paper, we study alternating regret in online convex optimization (OCO), motivated by the success of alternating learning dynamics in two-player games.
arXiv:2609.13547v1 Announce Type: new Abstract: We study switching regret in adversarial multi-armed bandits, where the learner competes with an arm sequence that changes at most $S$ times. When $S$...
arXiv:2610.20416v1 Announce Type: new Abstract: For the fundamental problem of prediction from expert advice, Freund asked whether one could compete with a comparator that switches $k$ times among on...