SOTAVerified

PAC learning

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 91–100 of 289 papers

TitleStatusHype
Find a witness or shatter: the landscape of computable PAC learning—0
Fine-Grained Distribution-Dependent Learning Curves—0
Forster Decomposition and Learning Halfspaces with Noise—0
From Local Pseudorandom Generators to Hardness of Learning—0
From PAC to Instance-Optimal Sample Complexity in the Plackett-Luce Model—0
Generalization Bounds for Data-Driven Numerical Linear Algebra—0
Hardness of Learning Boolean Functions from Label Proportions—0
Near-Optimal Statistical Query Hardness of Learning Halfspaces with Massart Noise—0
Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks—0
Distribution Learning Meets Graph Structure Sampling—0
Show:102550
← PrevPage 10 of 29Next →

No leaderboard results yet.