SOTAVerified

PAC learning

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 289 papers

TitleStatusHype
A Practical Theory of Generalization in Selectivity Learning—0
Revisiting Agnostic PAC Learning—0
Ramsey Theorems for Trees and a General 'Private Learning Implies Online Learning' Theorem—0
Superconstant Inapproximability of Decision Tree Learning—0
Distribution Learnability and Robustness—0
Credit Attribution and Stable Compression—0
Fast Rates for Bandit PAC Multiclass Classification—0
Is Efficient PAC Learning Possible with an Oracle That Responds 'Yes' or 'No'?—0
On the Computability of Robust PAC Learning—0
Optimistic Rates for Learning from Label ProportionsCode0
Weak Robust Compatibility Between Learning Algorithms and Counterfactual Explanation Generation Algorithms—0
On the Computational Landscape of Replicable Learning—0
Distribution Learning Meets Graph Structure Sampling—0
Efficient PAC Learnability of Dynamical Systems Over Multilayer Networks—0
Is Transductive Learning Equivalent to PAC Learning?—0
Error Exponent in Agnostic PAC Learning—0
On the Power of Interactive Proofs for Learning—0
On the Learnability of Out-of-distribution Detection—0
Super Non-singular Decompositions of Polynomials and their Application to Robustly Learning Low-degree PTFs—0
Hardness of Learning Boolean Functions from Label Proportions—0
List Sample Compression and Uniform Convergence—0
Towards a theory of model distillationCode0
Majority-of-Three: The Simplest Optimal Learner?—0
Proper vs Improper Quantum PAC learning—0
High-arity PAC learning via exchangeability—0
Show:102550
← PrevPage 3 of 12Next →

No leaderboard results yet.