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.
Efficient PAC Learnability of Dynamical Systems Over Multilayer Networks
Is Transductive Learning Equivalent to PAC Learning?
Error Exponent in Agnostic PAC Learning
On the Power of Interactive Proofs for Learning
On the Learnability of Out-of-distribution Detection
Super Non-singular Decompositions of Polynomials and their Application to Robustly Learning Low-degree PTFs
Hardness of Learning Boolean Functions from Label Proportions
List Sample Compression and Uniform Convergence
Towards a theory of model distillation
Majority-of-Three: The Simplest Optimal Learner?
Proper vs Improper Quantum PAC learning
High-arity PAC learning via exchangeability
Collaborative Learning with Different Labeling Functions
Private PAC Learning May be Harder than Online Learning
Transductive Learning Is Compact
The sample complexity of multi-distribution learning
$\varepsilon$-fractional Core Stability in Hedonic Games
Information-theoretic generalization bounds for learning from quantum data
Low-Rank MDPs with Continuous Action Spaces
A PAC Learning Algorithm for LTL and Omega-regular Objectives in MDPs
PAC Learning Linear Thresholds from Label Proportions
Overview of AdaBoost : Reconciling its views to better understand its dynamics
Distributional PAC-Learning from Nisan's Natural Proofs
User-Level Differential Privacy With Few Examples Per User
Provable learning of quantum states with graphical models
Computing the Vapnik Chervonenkis Dimension for Non-Discrete Settings
Efficiently Learning One-Hidden-Layer ReLU Networks via Schur Polynomials
The Sample Complexity of Multi-Distribution Learning for VC Classes
Optimal Learners for Realizable Regression: PAC Learning and Online Learning
Multiclass Boosting: Simple and Intuitive Weak Learning Criteria
Information-Computation Tradeoffs for Learning Margin Halfspaces with Random Classification Noise
Learnability with PAC Semantics for Multi-agent Beliefs
On the Role of Entanglement and Statistics in Learning
Agnostic Multi-Group Active Learning
Attribute-Efficient PAC Learning of Low-Degree Polynomial Threshold Functions with Nasty Noise
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.