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
PAC Learning Linear Thresholds from Label Proportions—0
PAC-Learning Uniform Ergodic Communicative Networks—0
PAC Learning, VC Dimension, and the Arithmetic Hierarchy—0
PAC Learning with Improvements—0
PAC learning with nasty noise—0
PAC learning with stable and private predictions—0
PAC Verification of Statistical Algorithms—0
Private Hypothesis Selection—0
A Characterization of Multiclass Learnability—0
A Characterization of Semi-Supervised Adversarially-Robust PAC Learnability—0
Towards a theory of out-of-distribution learning—0
Towards Efficient Contrastive PAC Learning—0
Towards Understanding Multi-Round Large Language Model Reasoning: Approximability, Learnability and Generalizability—0
Tree Learning: Optimal Algorithms and Sample Complexity—0
Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond—0
User-Level Differential Privacy With Few Examples Per User—0
-fractional Core Stability in Hedonic Games—0
VC Dimension and Distribution-Free Sample-Based Testing—0
Wasserstein Soft Label Propagation on Hypergraphs: Algorithm and Generalization Error Bounds—0
Weak Robust Compatibility Between Learning Algorithms and Counterfactual Explanation Generation Algorithms—0
Policy Synthesis and Reinforcement Learning for Discounted LTL—0
Predicting with Distributions—0
Predictive PAC Learning and Process Decompositions—0
Privacy-preserving Prediction—0
A Characterization of List Learnability—0
Show:102550
← PrevPage 9 of 12Next →

No leaderboard results yet.