SOTAVerified

PAC learning

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–175 of 289 papers

TitleStatusHype
Monotone Learning—0
Monotonic Learning in the PAC Framework: A New Perspective—0
More data speeds up training time in learning halfspaces over sparse vectors—0
Multiclass Boosting: Simple and Intuitive Weak Learning Criteria—0
Multiclass versus Binary Differentially Private PAC Learning—0
Multi-group Agnostic PAC Learnability—0
Multi-label Learning for Large Text Corpora using Latent Variable Model with Provable Gurantees—0
Multi-step learning and underlying structure in statistical models—0
Numerical and statistical analysis of NeuralODE with Runge-Kutta time integration—0
Of Dice and Games: A Theory of Generalized Boosting—0
On Agnostic PAC Learning in the Small Error Regime—0
On Agnostic PAC Learning using L_2-polynomial Regression and Fourier-based Algorithms—0
On computable learning of continuous features—0
On Fundamental Limits of Robust Learning—0
On Generalization Bounds of a Family of Recurrent Neural Networks—0
On Learnability with Computable Learners—0
On Learning and Enforcing Latent Assessment Models using Binary Feedback from Human Auditors Regarding Black-Box Classifiers—0
Online Learning and Disambiguations of Partial Concept Classes—0
Online Learning of k-CNF Boolean Functions—0
On PAC Learning Halfspaces in Non-interactive Local Privacy Model with Public Unlabeled Data—0
On the Complexity of Learning from Label Proportions—0
On the complexity of PAC learning in Hilbert spaces—0
On the Computability of Multiclass PAC Learning—0
On the Computability of Robust PAC Learning—0
On the Computational Landscape of Replicable Learning—0
Show:102550
← PrevPage 7 of 12Next →

No leaderboard results yet.