SOTAVerified

PAC learning

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 126–150 of 289 papers

TitleStatusHype
Learning Halfspaces with the Zero-One Loss: Time-Accuracy Tradeoffs—0
Learning Halfspaces with Tsybakov Noise—0
Learning Linear Attention in Polynomial Time—0
Learning multivariate Gaussians with imperfect advice—0
Learning Neural Networks with Two Nonlinear Layers in Polynomial Time—0
Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random—0
Learning pseudo-Boolean k-DNF and Submodular Functions—0
Learning Query Inseparable ELH Ontologies—0
Learning the hypotheses space from data through a U-curve algorithm—0
Learning the Hypotheses Space from data: Learning Space and U-curve Property—0
Learning Time Dependent Choice—0
Is Nash Equilibrium Approximator Learnable?—0
Learning under p-Tampering Attacks—0
Learning versus Refutation in Noninteractive Local Differential Privacy—0
Locally Private Learning without Interaction Requires Separation—0
Lifting uniform learners via distributional decomposition—0
List Learning with Attribute Noise—0
List Sample Compression and Uniform Convergence—0
From learnable objects to learnable random objects—0
Lower Bounds for Adversarially Robust PAC Learning—0
Low-Rank MDPs with Continuous Action Spaces—0
Majority-of-Three: The Simplest Optimal Learner?—0
Markov Decision Processes with Continuous Side Information—0
Measurability in the Fundamental Theorem of Statistical Learning—0
Metric Entropy Duality and the Sample Complexity of Outcome Indistinguishability—0
Show:102550
← PrevPage 6 of 12Next →

No leaderboard results yet.