paper-with-me

홈 › Papers

A Combinatorial Characterization of Supervised Online Learnability

2023-07-07 · Vinod Raman, Unique Subedi, Ambuj Tewari

We study the online learnability of hypothesis classes with respect to arbitrary, but bounded loss functions. No characterization of online learnability is known at this level of generality. We give a new scale-sensitive combinatorial dimension, named the sequential minimax dimension, and show that it gives a tight quantitative characterization of online learnability. In addition, we show that the sequential minimax dimension subsumes most existing combinatorial dimensions in online learning theory.

📄 PDF Abstract BibTeX arXiv:2307.03816

Code (0)

등록된 구현이 없습니다.

Tasks

Learning Theoryregression

Similar Papers 제목 키워드 기반

Online Learning: Random Averages, Combinatorial Parameters, and Learnability

2010-12-01 · NeurIPS 2010 12 · Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari

We develop a theory of online learning by defining several complexity measures. Among them are analogues of Rademacher complexity, covering numbers and fat-shattering dimension from statistical learning theory. Relations…

Learning Theory

Optimal Learners for Realizable Regression: PAC Learning and Online Learning

2023-07-07 · NeurIPS 2023 11 · Idan Attias, Steve Hanneke, Alkis Kalavasis, Amin Karbasi 외

In this work, we aim to characterize the statistical complexity of realizable regression both in the PAC learning setting and the online learning setting. Previous work had established the sufficiency of finiteness of th…

PAC learningregression

Inference for Gaussian Processes with Matern Covariogram on Compact Riemannian Manifolds

2023-09-21

In this work, we aim to characterize the statistical complexity of realizable regression both in the PAC learning setting and the online learning setting. Previous work had established the sufficiency of finiteness of th…

Gaussian ProcessesPAC learningregression

Inference for Gaussian Processes with Matern Covariogram on Compact Riemannian Manifolds

2023-09-21 · NeurIPS 2023 11

In this work, we aim to characterize the statistical complexity of realizable regression both in the PAC learning setting and the online learning setting. Previous work had established the sufficiency of finiteness of th…

Gaussian ProcessesPAC learningregression

Characterizing Online and Private Learnability under Distributional Constraints via Generalized Smoothness

2026-02-24 · Moïse Blanchard, Abhishek Shetty, Alexander Rakhlin arxiv

Understanding minimal assumptions that enable learning and generalization is perhaps the central question of learning theory. Several celebrated results in statistical learning theory, such as the VC theorem and Littlest…

Decision Making