SOTAVerified

PAC learning

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 201–225 of 289 papers

TitleStatusHype
Agnostic Learning of a Single Neuron with Gradient Descent—0
Proper Learning, Helly Number, and an Optimal SVM Bound—0
On the Complexity of Learning from Label Proportions—0
Closure Properties for Private Classification and Online Prediction—0
An Active Learning Framework for Constructing High-fidelity Mobility Maps—0
Adversarial Online Learning with Changing Action Sets: Efficient Algorithms with Approximate Regret Bounds—0
Decidability of Sample Complexity of PAC Learning in finite setting—0
On the Sample Complexity of Adversarial Multi-Source PAC Learning—0
Quantum statistical query learning—0
Best-item Learning in Random Utility Models with Subset Choices—0
Towards a combinatorial characterization of bounded memory learning—0
On Learnability with Computable Learners—0
Learning the Hypotheses Space from data: Learning Space and U-curve Property—0
On the Sample Complexity of Learning Sum-Product Networks—0
PAC learning with stable and private predictions—0
Sequential Mode Estimation with Oracle Queries—0
Learning Query Inseparable ELH Ontologies—0
On Generalization Bounds of a Family of Recurrent Neural Networks—0
Learning Concepts Definable in First-Order Logic with Counting—0
The Power of Comparisons for Actively Learning Linear Classifiers—0
Distribution-Independent PAC Learning of Halfspaces with Massart Noise—0
Query-driven PAC-Learning for Reasoning—0
Lower Bounds for Adversarially Robust PAC Learning—0
Private Hypothesis Selection—0
Regression EquilibriumCode0
Show:102550
← PrevPage 9 of 12Next →

No leaderboard results yet.