SOTAVerified

PAC learning

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

Papers

Showing 126150 of 289 papers

TitleStatusHype
Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond0
Analyzing Robustness of Angluin's L* Algorithm in Presence of Noise0
On PAC Learning Halfspaces in Non-interactive Local Privacy Model with Public Unlabeled Data0
Fine-Grained Distribution-Dependent Learning Curves0
Cryptographic Hardness of Learning Halfspaces with Massart Noise0
Generalization Bounds for Data-Driven Numerical Linear Algebra0
PAC Generalization via Invariant Representations0
Bézier Flow: a Surface-wise Gradient Descent Method for Multi-objective Optimization0
Sample Complexity Bounds for Robustly Learning Decision Lists against Evasion Attacks0
VICE: Variational Interpretable Concept EmbeddingsCode1
Clifford Circuits can be Properly PAC Learned if and only if RP=NP0
Active-learning-based non-intrusive Model Order Reduction0
Metric Entropy Duality and the Sample Complexity of Outcome Indistinguishability0
A Characterization of Multiclass Learnability0
Adversarially Robust Learning with Tolerance0
On Learning and Enforcing Latent Assessment Models using Binary Feedback from Human Auditors Regarding Black-Box Classifiers0
A Characterization of Semi-Supervised Adversarially-Robust PAC Learnability0
Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks0
Monotone Learning0
Planted Dense Subgraphs in Dense Random Graphs Can Be Recovered using Graph-based Machine LearningCode0
Efficiently Learning One Hidden Layer ReLU Networks From Queries0
Exponential Separation between Two Learning Models and Adversarial Robustness0
On computable learning of continuous features0
PAC-Learning Uniform Ergodic Communicative Networks0
Realizable Learning is All You Need0
Show:102550
← PrevPage 6 of 12Next →

No leaderboard results yet.