arXiv Machine Learning

Local Regularization Does Not Characterize Multiclass PAC Learnability

arXiv:2607. 23449v1 Announce Type: new Abstract: Local regularization assigns each hypothesis a test-point-dependent score and predicts with a minimum-score hypothesis consistent with the sample.

arXiv Machine Learning
Aug 28

Algorithmic Principles For Multiclass Learning Are Hard To Come By: Limits of Regularization and Proper Learning

The paper investigates fundamental limits of algorithmic principles in multiclass learning, specifically proper learning and regularization. It shows that learning cannot always be reduced to proper learning even with an enlarged hypothesis class, that proper learners may need a sublinear number of errors that can be arbitrarily large, and that regularization (SRM or local) is not universally sufficient. The authors also provide a positive theory giving sufficient conditions for SRM learnability and a characterization via integrability of revealed preferences.

By Julian Asilis, Shaddin Dughmi, Vatsal Sharan, Alec Sun, Shang-Hua Teng, Chang Wang
arXiv Machine Learning
Jun 29

Surprises in Proper Positive-Only Learning

arXiv:2606. 28309v1 Announce Type: cross Abstract: Binary classification from positive-only samples is a variant of PAC learning in which the learner receives i.

By Shai Ben-David, Farnam Mansouri, Anay Mehrotra, Manolis Zampetakis
arXiv Machine Learning
Jul 9

The Optimal Sample Complexity of Learning Autoregressive Chain-of-Thought

arXiv:2607. 07423v1 Announce Type: new Abstract: We prove that, in the realizable PAC setting, the sample complexity of exact-trace learning for full autoregressive Chain-of-Thought traces is upper bounded by the standard multiclass rate of the local next-token class, where this rate is governed by the Daniely--Shalev-Shwartz dimension.

By Zhiyuan Li
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.

By Julian Asilis, Shaddin Dughmi, Chirag Pabbaraju
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).