arXiv Machine Learning
Aug 7
Optimal Rates for Learning with Monotone Adversaries
arXiv:2608. 06337v1 Announce Type: cross Abstract: A monotone adversary observes an i.
Adversarial Online Classification with a Preview
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.
Related stories
arXiv Machine Learning
Oct 8
Optimal Regret for Online Market Making with Limit Order Book
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 Machine Learning
Jun 17
On Randomized Algorithms in Online Strategic Classification
arXiv:2602. 06257v2 Announce Type: replace Abstract: Online strategic classification studies settings in which agents strategically modify their features to obtain favorable predictions.
arXiv Machine Learning
Oct 8
Oracle-Efficient and Parameter-Free Agnostic Smoothed Online Learning
arXiv:2610. 10499v1 Announce Type: new Abstract: Online learning is an attractive framework in many domains because it permits well-defined learning even when data are dependent or chosen adversarially.
arXiv Machine Learning
Aug 14
Bagging Robustly Learns VC Classes with Linear Sample Complexity
arXiv:2608. 13514v1 Announce Type: cross Abstract: We revisit the problem of learning predictors robust to adversarial examples at test-time.
arXiv Statistics ML
Oct 26
Optimal Multiclass Online Regret with Arbitrary Label Spaces
arXiv:2610. 32339v1 Announce Type: cross Abstract: We determine the optimal regret in agnostic multiclass online learning with arbitrary, possibly infinite, label spaces.
Hugging Face Trending Papers
Sep 21
Adversarially Robust PAC Learning with Optimal VC Rates
We study the problem of \emph{adversarially robust} PAC learning. In this framework, the learner observes independent samples from an unknown distribution over $\mathcal{X} \times \{0,1\}$, as in clas...
Hugging Face Trending Papers
Aug 13
Bagging Robustly Learns VC Classes with Linear Sample Complexity
We revisit the problem of learning predictors robust to adversarial examples at test-time. We prove that VC classes are adversarially robustly learnable with sample complexity linear in the VC dimension $d$, providing an exponential improvement over the previous upper bound of Montasser, Hanneke, and Srebro (2019).
arXiv Machine Learning
Aug 4
Dense Language Generation Made Simple: Deterministic, Randomized, and Multi-Order Algorithms
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 Machine Learning
Aug 24
When Clean Data Hurts: Learning with Monotone Corruptions Beyond Binary Classification
The paper investigates learning with monotone adversarial corruptions, extending previous binary classification results to multiclass and partial binary settings. It shows that even a small number of strategically inserted corrupted examples can render a learnable multiclass problem with DS dimension 2 completely unlearnable, and provides matching upper bounds when the adversary’s budget is sublinear. The work also demonstrates that classic error rates remain attainable under bounded or limited‑view adversaries.
arXiv Machine Learning
Jun 16
Online Realizable Regression and Applications for ReLU Networks
arXiv:2602. 19172v2 Announce Type: replace Abstract: Realizable online regression can behave very differently from online classification.
arXiv Machine Learning
Oct 19
No-Regret Language Generation
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.