SOTAVerified

PAC learning

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–175 of 289 papers

TitleStatusHype
Quantum Boosting using Domain-Partitioning HypothesesCode0
Active Learning for Contextual Search with Binary Feedbacks—0
Towards a theory of out-of-distribution learning—0
Learning the hypotheses space from data through a U-curve algorithm—0
Learning General Halfspaces with General Massart Noise under the Gaussian Distribution—0
Is Nash Equilibrium Approximator Learnable?—0
Statistically Near-Optimal Hypothesis Selection—0
On the Power of Differentiable Learning versus PAC and SQ Learning—0
Multiclass versus Binary Differentially Private PAC Learning—0
A Theory of PAC Learnability of Partial Concept Classes—0
Forster Decomposition and Learning Halfspaces with Noise—0
Semi-verified PAC Learning from the Crowd—0
Supervising the Transfer of Reasoning Patterns in VQA—0
Multi-group Agnostic PAC Learnability—0
Incentive-aware PAC learning—0
Learning and Certification under Instance-targeted Poisoning—0
Broadly Applicable Targeted Data Sample Omission Attacks—0
Symbolic Abstractions From Data: A PAC Learning Approach—0
PAC-learning gains of Turing machines over circuits and neural networks—0
Robust learning under clean-label attack—0
Private learning implies quantum stability—0
Sample-Optimal PAC Learning of Halfspaces with Malicious Noise—0
On Agnostic PAC Learning using L_2-polynomial Regression and Fourier-based Algorithms—0
Fairness-Aware PAC Learning from Corrupted Data—0
Adversarial Robustness: What fools you makes you stronger—0
Show:102550
← PrevPage 7 of 12Next →

No leaderboard results yet.