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
Efficiently Learning One-Hidden-Layer ReLU Networks via Schur Polynomials—0
The Sample Complexity of Multi-Distribution Learning for VC Classes—0
Optimal Learners for Realizable Regression: PAC Learning and Online Learning—0
Multiclass Boosting: Simple and Intuitive Weak Learning Criteria—0
Information-Computation Tradeoffs for Learning Margin Halfspaces with Random Classification Noise—0
Learnability with PAC Semantics for Multi-agent Beliefs—0
On the Role of Entanglement and Statistics in Learning—0
Agnostic Multi-Group Active Learning—0
Attribute-Efficient PAC Learning of Low-Degree Polynomial Threshold Functions with Nasty Noise—0
On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences—0
Show:102550
← PrevPage 10 of 29Next →

No leaderboard results yet.