arXiv:2610.09691v1 Announce Type: cross Abstract: We study online learning in market making, where, at each round, a market maker posts bid and ask prices before observing the market price and the pr...
The paper presents upper and lower bounds on the regret for m‑set adversarial bandits across various utilities—winner reward or sum of rewards—and feedback models, including winner index, winner reward, sum of rewards, and their combinations. By comparing these results to standard bounds for combinatorial and MNL bandits, the authors demonstrate that small changes in the setting can dramatically affect learning rates. The main technical contribution is the derivation of information‑theoretic lower bounds, and synthetic experiments validate the theoretical findings.
arXiv:2608. 12231v2 Announce Type: replace Abstract: We study adversarial combinatorial bandits with $m$-set actions, where at each round the learner selects $m$ out of $d$ items and observes only the aggregate loss of the selected items.
arXiv:2608. 06337v1 Announce Type: cross Abstract: A monotone adversary observes an i.
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:2605. 09200v2 Announce Type: replace Abstract: We study adversarial noisy bandits given a known function class $\mathcal{F}$.
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:2602. 06257v2 Announce Type: replace Abstract: Online strategic classification studies settings in which agents strategically modify their features to obtain favorable predictions.
arXiv:2510. 22819v3 Announce Type: replace Abstract: The convergence analysis of online learning algorithms is central to machine learning theory, where the last-iterate convergence is particularly important, as it captures the learner's actual decisions and describes the evolution of the learning process over time.
The paper investigates preference-based bandits where a learner selects pairs of arms and receives binary preference feedback modeled by Bradley–Terry. It introduces the locally sensitive eluder dimension, a new complexity measure for logistic preference feedback, and proposes the GINOP algorithm that uses log-loss confidence sets to balance optimism and exploration. The authors prove a first-order regret bound showing that learning with preference feedback can be as statistically efficient as learning from direct rewards, and they validate their theory with empirical experiments.
arXiv:2609. 15248v2 Announce Type: replace-cross Abstract: In bandits with probing, a learner selects at most $k$ of $n$ arms per round, earns the largest of their rewards, and competes with the best fixed single arm.
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.