SOTAVerified

PAC learning

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 121–130 of 289 papers

TitleStatusHype
A Characterization of List Learnability—0
Privacy Induces Robustness: Information-Computation Gaps and Sparse Mean EstimationCode0
Is Out-of-Distribution Detection Learnable?—0
Learning versus Refutation in Noninteractive Local Differential Privacy—0
SQ Lower Bounds for Learning Single Neurons with Massart Noise—0
Superpolynomial Lower Bounds for Decision Tree Learning and Testing—0
Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond—0
Analyzing Robustness of Angluin's L* Algorithm in Presence of Noise—0
On PAC Learning Halfspaces in Non-interactive Local Privacy Model with Public Unlabeled Data—0
Fine-Grained Distribution-Dependent Learning Curves—0
Show:102550
← PrevPage 13 of 29Next →

No leaderboard results yet.