SOTAVerified

PAC learning

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 251–275 of 289 papers

TitleStatusHype
Collaborative PAC Learning—0
Markov Decision Processes with Continuous Side Information—0
A learning problem that is independent of the set theory ZFC axioms—0
Learning under p-Tampering Attacks—0
An Approach to One-Bit Compressed Sensing Based on Probably Approximately Correct Learning Theory—0
Learning Neural Networks with Two Nonlinear Layers in Polynomial Time—0
Agnostic Learning by Refuting—0
Learning Geometric Concepts with Nasty Noise—0
Sample-Efficient Learning of Mixtures—0
On Fundamental Limits of Robust Learning—0
Efficient PAC Learning from the Crowd—0
On the Power of Learning from k-Wise Queries—0
Multi-step learning and underlying structure in statistical models—0
Predicting with Distributions—0
Simultaneous Private Learning of Multiple Concepts—0
Fast Collaborative Filtering from Implicit Feedback with Provable Guarantees—0
PAC Learning-Based Verification and Model Synthesis—0
Hardness of Online Sleeping Combinatorial Optimization Problems—0
The Optimal Sample Complexity of PAC Learning—0
Order-Revealing Encryption and the Hardness of Private Learning—0
Differentially Private Release and Learning of Threshold Functions—0
Tight Bounds on Low-degree Spectral Concentration of Submodular and XOS functions—0
The VC-Dimension of Similarity Hypotheses Spaces—0
PAC Learning, VC Dimension, and the Arithmetic Hierarchy—0
Online Learning of k-CNF Boolean Functions—0
Show:102550
← PrevPage 11 of 12Next →

No leaderboard results yet.