SOTAVerified

PAC learning

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 276–289 of 289 papers

TitleStatusHype
Sample Complexity Bounds on Differentially Private Learning via Communication Complexity—0
Distribution-Independent Reliable Learning—0
Characterizing the Sample Complexity of Private Learners—0
More data speeds up training time in learning halfspaces over sparse vectors—0
Predictive PAC Learning and Process Decompositions—0
Optimal Bounds on Approximation of Submodular and XOS Functions by Juntas—0
Representation, Approximation and Learning of Submodular Functions Using Low-rank Decision Trees—0
Learning Halfspaces with the Zero-One Loss: Time-Accuracy Tradeoffs—0
Learning pseudo-Boolean k-DNF and Submodular Functions—0
Learning DNF Expressions from Fourier Spectrum—0
A Unified Framework for Approximating and Clustering Data—0
A Complete Characterization of Statistical Query Learning with Applications to Evolvability—0
Introduction to Machine Learning: Class Notes 67577Code0
PAC learning with nasty noise—0
Show:102550
← PrevPage 12 of 12Next →

No leaderboard results yet.