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.
Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random
A Closer Look at the Learnability of Out-of-Distribution (OOD) Detection
Monotonic Learning in the PAC Framework: A New Perspective
Ensuring superior learning outcomes and data security for authorized learner
Of Dice and Games: A Theory of Generalized Boosting
Implicit High-Order Moment Tensor Estimation and Learning Latent Variable Models
Effective Littlestone Dimension
Probably Approximately Precision and Recall Learning
Learning multivariate Gaussians with imperfect advice
Reliable Learning of Halfspaces under Gaussian Marginals
Probably approximately correct high-dimensional causal effect estimation given a valid adjustment set
Prospective Learning: Learning for a Dynamic Future
Screw Geometry Meets Bandits: Incremental Acquisition of Demonstrations to Generate Manipulation Plans
Enhancing PAC Learning of Half spaces Through Robust Optimization Techniques
Learning Linear Attention in Polynomial Time
Measurability in the Fundamental Theorem of Statistical Learning
Strategic Classification With Externalities
Agnostic Smoothed Online Learning
Fill In The Gaps: Model Calibration and Generalization with Synthetic Data
Efficient PAC Learning of Halfspaces with Constant Malicious Noise Rate
Efficient Statistics With Unknown Truncation, Polynomial Time Algorithms, Beyond Gaussians
Derandomizing Multi-Distribution Learning
Fast decision tree learning solves hard coding-theoretic problems
A Practical Theory of Generalization in Selectivity Learning
Revisiting Agnostic PAC Learning
Ramsey Theorems for Trees and a General 'Private Learning Implies Online Learning' Theorem
Superconstant Inapproximability of Decision Tree Learning
Distribution Learnability and Robustness
Credit Attribution and Stable Compression
Fast Rates for Bandit PAC Multiclass Classification
Is Efficient PAC Learning Possible with an Oracle That Responds 'Yes' or 'No'?
On the Computability of Robust PAC Learning
Optimistic Rates for Learning from Label Proportions
Weak Robust Compatibility Between Learning Algorithms and Counterfactual Explanation Generation Algorithms
On the Computational Landscape of Replicable Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.