SOTAVerified

PAC learning

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 276–289 of 289 papers

TitleStatusHype
A Characterization of List Learnability—0
Weak Robust Compatibility Between Learning Algorithms and Counterfactual Explanation Generation Algorithms—0
A Characterization of Multiclass Learnability—0
A Characterization of Semi-Supervised Adversarially-Robust PAC Learnability—0
A Closer Look at the Learnability of Out-of-Distribution (OOD) Detection—0
A Complete Characterization of Statistical Query Learning with Applications to Evolvability—0
A Computational Separation between Private Learning and Online Learning—0
Active-learning-based non-intrusive Model Order Reduction—0
Active Learning for Contextual Search with Binary Feedbacks—0
A Distributional-Lifting Theorem for PAC Learning—0
Adversarial Laws of Large Numbers and Optimal Regret in Online Classification—0
Adversarially Robust Learning with Tolerance—0
Adversarial Online Learning with Changing Action Sets: Efficient Algorithms with Approximate Regret Bounds—0
Adversarial Robustness: What fools you makes you stronger—0
Show:102550
← PrevPage 12 of 12Next →

No leaderboard results yet.