paper-with-me

홈 › Papers

A Theory of Universal Agnostic Learning

2026-01-28 · Steve Hanneke, Shay Moran arxiv

We provide a complete theory of optimal universal rates for binary classification in the agnostic setting. This extends the realizable-case theory of Bousquet, Hanneke, Moran, van Handel, and Yehudayoff (2021) by removing the realizability assumption on the distribution. We identify a fundamental tetrachotomy of optimal rates: for every concept class, the optimal universal rate of convergence of the excess error rate is one of $e^{-n}$, $e^{-o(n)}$, $o(n^{-1/2})$, or arbitrarily slow. We further identify simple combinatorial structures which determine which of these categories any given concept class falls into.

📄 PDF Abstract BibTeX arXiv:2601.20961

Code (0)

등록된 구현이 없습니다.

Tasks

Binary Classification

Similar Papers 제목 키워드 기반

Universal Rates of ERM for Agnostic Learning

2025-06-17 · Steve Hanneke, Mingyue Xu

The universal learning framework has been developed to obtain guarantees on the learning rates that hold for any fixed distribution, which can be much faster than the ones uniformly hold over all the distributions. Given…

Binary Classification

Persistence diagrams of random matrices via Morse theory: universality and a new spectral diagnostic

2026-03-29 · Matthew Loftus arxiv

We prove that the persistence diagram of the sublevel set filtration of the quadratic form f(x) = x^T M x restricted to the unit sphere S^{n-1} is analytically determined by the eigenvalues of the symmetric matrix M. By …

A Theory of Optimistically Universal Online Learnability for General Concept Classes

2025-01-15 · Steve Hanneke, Hongao Wang

We provide a full characterization of the concept classes that are optimistically universally online learnable with $\{0, 1\}$ labels. The notion of optimistically universal online learning was defined in [Hanneke, 2021]…

Philosophy

Universal Equivariant Multilayer Perceptrons

2020-02-07 · ICML 2020 1 · Siamak Ravanbakhsh

Group invariant and equivariant Multilayer Perceptrons (MLP), also known as Equivariant Networks, have achieved remarkable success in learning on a variety of data structures, such as sequences, images, sets, and graphs.…

Computable universal online learning

2025-10-21 · Dariusz Kalociński, Tomasz Steifer arxiv

Understanding when learning is possible is a fundamental task in the theory of machine learning. However, many characterizations known from the literature deal with abstract learning as a mathematical object and ignore t…

Binary Classification