← Back to all news
arXiv Machine Learning By Julian Asilis, Shaddin Dughmi, Vatsal Sharan, Alec Sun, Shang-Hua Teng, Chang Wang

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

Read the original on arXiv Machine 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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

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
safety
More like this →
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
More like this →
arXiv Machine Learning
Sep 11

Relatively Smart II: Tractable or Semi-Supervised Instance-Optimal Learning

The paper extends the study of relatively smart learning, showing that ERM and any proper consistent learner are relatively smart for binary classification in the distribution‑free setting, achieving a quadratic sample‑complexity blowup. It further demonstrates that semi‑supervised relatively smart learning is possible with only a quadratic blowup in unlabeled data and no blowup in labeled data, though this requires a leave‑most‑out transductive approach and incurs intractability when only an agnostic ERM oracle is available. The results clarify the trade‑offs between sample efficiency, label efficiency, and computational tractability in relatively smart learning.

By Shaddin Dughmi, Alireza F. Pour
More like this →
arXiv Machine Learning
Jul 7

A Hierarchy of Policy Learning Problems

arXiv:2607. 03385v1 Announce Type: cross Abstract: Policy learning has received substantial attention with the goal of learning policies from observational data for decision-making.

By Hamsa Bastani, Osbert Bastani, Shihan Chen
More like this →
arXiv Machine Learning
Oct 15

Dimension-Free Scaling Laws for Size Generalization: An Exponential Separation

The paper introduces a statistical learning theory for size generalization in models that handle variable-size structured data such as sets and graphs. It proves an exponential separation in sample complexity: polynomial in-domain learning yields only logarithmic decay in size-generalization error, while an exponential source condition restores polynomial decay. These results provide dimension‑free scaling laws and optimal minimax bounds for transferring learning across input sizes.

By Behrooz Tahmasebi, Melanie Weber
More like this →