SOTAVerified

PAC learning

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 289 papers

TitleStatusHype
A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise—0
An Optimal Elimination Algorithm for Learning a Best Arm—0
A packing lemma for VCN_k-dimension and learning high-dimensional data—0
A PAC Learning Algorithm for LTL and Omega-regular Objectives in MDPs—0
A Parameterized Theory of PAC Learning—0
A Polynomial Time Algorithm for Learning Halfspaces with Tsybakov Noise—0
Agnostic Multi-Group Active Learning—0
A Strongly Polynomial Algorithm for Approximate Forster Transforms and its Application to Halfspace Learning—0
A Theory of PAC Learnability of Partial Concept Classes—0
Attribute-Efficient PAC Learning of Low-Degree Polynomial Threshold Functions with Nasty Noise—0
Attribute-Efficient PAC Learning of Sparse Halfspaces with Constant Malicious Noise Rate—0
A Unified Framework for Approximating and Clustering Data—0
Bagging is an Optimal PAC Learner—0
Bandit Multiclass List Classification—0
Best-item Learning in Random Utility Models with Subset Choices—0
Bézier Flow: a Surface-wise Gradient Descent Method for Multi-objective Optimization—0
Broadly Applicable Targeted Data Sample Omission Attacks—0
Can SGD Learn Recurrent Neural Networks with Provable Generalization?—0
Characterizing the Sample Complexity of Private Learners—0
Clifford Circuits can be Properly PAC Learned if and only if RP=NP—0
Closure Properties for Private Classification and Online Prediction—0
Collaborative Learning with Different Labeling Functions—0
Collaborative PAC Learning—0
Communication-Aware Collaborative Learning—0
Active Learning for Contextual Search with Binary Feedbacks—0
Show:102550
← PrevPage 2 of 12Next →

No leaderboard results yet.