SOTAVerified

PAC learning

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

Papers

Showing 251275 of 289 papers

TitleStatusHype
Superpolynomial Lower Bounds for Decision Tree Learning and Testing0
Supervising the Transfer of Reasoning Patterns in VQA0
Symbolic Abstractions From Data: A PAC Learning Approach0
The Optimal Sample Complexity of PAC Learning0
The Power of Comparisons for Actively Learning Linear Classifiers0
The Price is (Probably) Right: Learning Market Equilibria from Samples0
The Sample Complexity of Multi-Distribution Learning for VC Classes0
The sample complexity of multi-distribution learning0
The VC-Dimension of Similarity Hypotheses Spaces0
The working principles of model-based GAs fall within the PAC framework: A mathematical theory of problem decomposition0
Learning General Halfspaces with General Massart Noise under the Gaussian Distribution0
Tight Bounds for Collaborative PAC Learning via Multiplicative Weights0
Tight Bounds on Low-degree Spectral Concentration of Submodular and XOS functions0
Tight Lower Bounds for Locally Differentially Private Selection0
Towards a combinatorial characterization of bounded memory learning0
Towards a Combinatorial Characterization of Bounded-Memory Learning0
Towards a theory of out-of-distribution learning0
Towards Efficient Contrastive PAC Learning0
Towards Understanding Multi-Round Large Language Model Reasoning: Approximability, Learnability and Generalizability0
Tree Learning: Optimal Algorithms and Sample Complexity0
Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond0
User-Level Differential Privacy With Few Examples Per User0
-fractional Core Stability in Hedonic Games0
VC Dimension and Distribution-Free Sample-Based Testing0
Wasserstein Soft Label Propagation on Hypergraphs: Algorithm and Generalization Error Bounds0
Show:102550
← PrevPage 11 of 12Next →

No leaderboard results yet.