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:2610. 32339v1 Announce Type: cross Abstract: We determine the optimal regret in agnostic multiclass online learning with arbitrary, possibly infinite, label spaces.
arXiv:2608. 01320v1 Announce Type: cross Abstract: Language generation in the limit is a theoretical framework for studying how a generator can learn to produce new valid strings from a stream of positive examples.
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:2606. 25777v1 Announce Type: cross Abstract: We initiate a resource-aware theory of \textit{language generation in the limit} under the minimal constraint of space efficiency.
The paper studies robust bandits, a framework for learning when the true environment lies outside the learner’s hypothesis class. It presents a polynomial‑time algorithm achieving ≠O(√T) regret for a specific tractable case, while showing that slight extensions of this case are NP‑hard. The work highlights the computational limits of robust bandits and suggests their relevance to AI alignment.
arXiv:2609.27206v1 Announce Type: cross Abstract: Prediction with expert advice is a fundamental problem in online learning. When the time horizon $T$ is known in advance, the minimax cumulative regr...
The paper presents an efficient algorithm for repeated prophet inequalities with prefix feedback, achieving “~O(√T) expected regret”. It uses empirical backward induction, box‑specific reach bonuses, and a relative‑drop aggregation rule to eliminate polynomial dependence on the number of boxes. This resolves an open question from Liu et al. (2025).
arXiv:2607. 23361v1 Announce Type: cross Abstract: Language generation in the limit is an elegant model introduced by Kleinberg and Mullainathan [KM24] to formally study language generation by an algorithm that learns solely based on example strings.
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:2602. 06257v2 Announce Type: replace Abstract: Online strategic classification studies settings in which agents strategically modify their features to obtain favorable predictions.
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...
arXiv:2507. 22854v3 Announce Type: replace-cross Abstract: We propose novel classical and quantum online algorithms for learning finite- and infinite-horizon Markov Decision Processes (MDPs).