Papers with Code 아카이브
PAC learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Probably Approximately Correct (PAC) learning analyzes machine learning mathematically using probability bounds.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Active-learning-based non-intrusive Model Order Reduction
Metric Entropy Duality and the Sample Complexity of Outcome Indistinguishability
A Characterization of Multiclass Learnability
Adversarially Robust Learning with Tolerance
On Learning and Enforcing Latent Assessment Models using Binary Feedback from Human Auditors Regarding Black-Box Classifiers
A Characterization of Semi-Supervised Adversarially-Robust PAC Learnability
Monotone Learning
Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks
Planted Dense Subgraphs in Dense Random Graphs Can Be Recovered using Graph-based Machine Learning
On computable learning of continuous features
PAC-Learning Uniform Ergodic Communicative Networks
Realizable Learning is All You Need
Quantum Boosting using Domain-Partitioning Hypotheses
Active Learning for Contextual Search with Binary Feedbacks
Towards a theory of out-of-distribution learning
Learning the hypotheses space from data through a U-curve algorithm
Learning General Halfspaces with General Massart Noise under the Gaussian Distribution
Is Nash Equilibrium Approximator Learnable?
Statistically Near-Optimal Hypothesis Selection
On the Power of Differentiable Learning versus PAC and SQ Learning
Multiclass versus Binary Differentially Private PAC Learning
A Theory of PAC Learnability of Partial Concept Classes
Forster Decomposition and Learning Halfspaces with Noise
Semi-verified PAC Learning from the Crowd
Supervising the Transfer of Reasoning Patterns in VQA
Multi-group Agnostic PAC Learnability
Learning and Certification under Instance-targeted Poisoning
Broadly Applicable Targeted Data Sample Omission Attacks
Symbolic Abstractions From Data: A PAC Learning Approach
PAC-learning gains of Turing machines over circuits and neural networks
Robust learning under clean-label attack
Private learning implies quantum stability
Fairness-Aware PAC Learning from Corrupted Data
Sample-Optimal PAC Learning of Halfspaces with Malicious Noise
On Agnostic PAC Learning using $\mathcal{L}_2$-polynomial Regression and Fourier-based Algorithms
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.