SOTAVerified

PAC learning

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 289 papers

TitleStatusHype
Optimistic Rates for Learning from Label ProportionsCode0
Quantum Boosting using Domain-Partitioning HypothesesCode0
Understanding Boolean Function Learnability on Deep Neural Networks: PAC Learning Meets Neurosymbolic ModelsCode0
Agnostic Learning of a Single Neuron with Gradient Descent—0
Agnostic Learning by Refuting—0
Active-learning-based non-intrusive Model Order Reduction—0
Adversarial Robustness: What fools you makes you stronger—0
Adversarial Online Learning with Changing Action Sets: Efficient Algorithms with Approximate Regret Bounds—0
A Computational Separation between Private Learning and Online Learning—0
A Characterization of Semi-Supervised Adversarially-Robust PAC Learnability—0
Show:102550
← PrevPage 2 of 29Next →

No leaderboard results yet.