SOTAVerified

PAC learning

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 289 papers

TitleStatusHype
Computational-Statistical Tradeoffs from NP-hardness—0
A Distributional-Lifting Theorem for PAC Learning—0
Conservative classifiers do consistently well with improving agents: characterizing statistical and online learning—0
Attribute-Efficient PAC Learning of Sparse Halfspaces with Constant Malicious Noise Rate—0
Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-index Models—0
A packing lemma for VCN_k-dimension and learning high-dimensional data—0
From learnable objects to learnable random objects—0
Lean Formalization of Generalization Error Bound by Rademacher ComplexityCode1
Numerical and statistical analysis of NeuralODE with Runge-Kutta time integration—0
Towards Understanding Multi-Round Large Language Model Reasoning: Approximability, Learnability and Generalizability—0
PAC Learning with Improvements—0
A Linear Theory of Multi-Winner Voting—0
Contrastive Learning with Nasty Noise—0
Towards Efficient Contrastive PAC Learning—0
On Agnostic PAC Learning in the Small Error Regime—0
Bandit Multiclass List Classification—0
Simplifying Adversarially Robust PAC Learning with Tolerance—0
On the Computability of Multiclass PAC Learning—0
Data-Driven Neural Certificate Synthesis—0
Efficient Optimal PAC Learning—0
PAC Learning is just Bipartite Matching (Sort of)—0
Distribution-Specific Agnostic Conditional Classification With Halfspaces—0
Ehrenfeucht-Haussler Rank and Chain of Thought—0
The working principles of model-based GAs fall within the PAC framework: A mathematical theory of problem decomposition—0
Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random—0
Show:102550
← PrevPage 1 of 12Next →

No leaderboard results yet.