SOTAVerified

PAC learning

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–125 of 289 papers

TitleStatusHype
High-arity PAC learning via exchangeability—0
How to Use Heuristics for Differential Privacy—0
Identifying Information from Observations with Uncertainty and Novelty—0
Implicit High-Order Moment Tensor Estimation and Learning Latent Variable Models—0
Improved Algorithms for Collaborative PAC Learning—0
Incentive-aware PAC learning—0
Inference for Gaussian Processes with Matern Covariogram on Compact Riemannian Manifolds—0
Inference for Gaussian Processes with Matern Covariogram on Compact Riemannian Manifolds—0
Information-Computation Tradeoffs for Learning Margin Halfspaces with Random Classification Noise—0
Information-theoretic generalization bounds for learning from quantum data—0
Distribution Learning Meets Graph Structure Sampling—0
Is Efficient PAC Learning Possible with an Oracle That Responds 'Yes' or 'No'?—0
Is Out-of-Distribution Detection Learnable?—0
Is Transductive Learning Equivalent to PAC Learning?—0
A Strongly Polynomial Algorithm for Approximate Forster Transforms and its Application to Halfspace Learning—0
Learnability can be undecidable—0
Transductive Learning Is Compact—0
Learnability with PAC Semantics for Multi-agent Beliefs—0
Learnable: Theory vs Applications—0
Learning and Certification under Instance-targeted Poisoning—0
Learning, compression, and leakage: Minimising classification error via meta-universal compression principles—0
Learning Concepts Definable in First-Order Logic with Counting—0
Learning DNF Expressions from Fourier Spectrum—0
Learning from Mixtures of Private and Public Populations—0
Agnostic PAC Learning of k-juntas Using L2-Polynomial Regression—0
Show:102550
← PrevPage 5 of 12Next →

No leaderboard results yet.