SOTAVerified

PAC learning

Probably Approximately Correct (PAC) learning analyzes machine learning mathematically using probability bounds.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 289 papers

TitleStatusHype
Computational-Statistical Tradeoffs from NP-hardness—0
Computing the Vapnik Chervonenkis Dimension for Non-Discrete Settings—0
Conservative classifiers do consistently well with improving agents: characterizing statistical and online learning—0
Contrastive Learning with Nasty Noise—0
Credit Attribution and Stable Compression—0
Crowdsourced PAC Learning under Classification Noise—0
Cryptographic Hardness of Learning Halfspaces with Massart Noise—0
Data-Driven Neural Certificate Synthesis—0
Decidability of Sample Complexity of PAC Learning in finite setting—0
Derandomizing Multi-Distribution Learning—0
Differentially Private Learning of Geometric Concepts—0
Differentially Private Release and Learning of Threshold Functions—0
Attribute-Efficient PAC Learning of Sparse Halfspaces with Constant Malicious Noise Rate—0
Attribute-Efficient PAC Learning of Low-Degree Polynomial Threshold Functions with Nasty Noise—0
Agnostic Smoothed Online Learning—0
A Distributional-Lifting Theorem for PAC Learning—0
Effective Littlestone Dimension—0
Do PAC-Learners Learn the Marginal Distribution?—0
A Theory of PAC Learnability of Partial Concept Classes—0
Distribution-Specific Agnostic Conditional Classification With Halfspaces—0
Efficiently Learning One Hidden Layer ReLU Networks From Queries—0
Efficiently Learning One-Hidden-Layer ReLU Networks via Schur Polynomials—0
Efficient Optimal PAC Learning—0
Efficient PAC Learnability of Dynamical Systems Over Multilayer Networks—0
Distribution Learning Meets Graph Structure Sampling—0
Show:102550
← PrevPage 3 of 12Next →

No leaderboard results yet.