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.
Policy Synthesis and Reinforcement Learning for Discounted LTL
SAT-Based PAC Learning of Description Logic Concepts
A Parameterized Theory of PAC Learning
Probably Approximately Correct Federated Learning
Online Learning and Disambiguations of Partial Concept Classes
Lifting uniform learners via distributional decomposition
Stability is Stable: Connections between Replicability, Privacy, and Adaptive Generalization
Agnostic PAC Learning of k-juntas Using L2-Polynomial Regression
On the complexity of PAC learning in Hilbert spaces
Do PAC-Learners Learn the Marginal Distribution?
Tree Learning: Optimal Algorithms and Sample Complexity
Find a witness or shatter: the landscape of computable PAC learning
PAC learning and stabilizing Hedonic Games: towards a unifying approach
Optimal lower bounds for Quantum Learning via Information Theory
A Strongly Polynomial Algorithm for Approximate Forster Transforms and its Application to Halfspace Learning
Bagging is an Optimal PAC Learner
PAC Verification of Statistical Algorithms
Comparative Learning: A Sample Complexity Theory for Two Hypothesis Classes
On Proper Learnability between Average- and Worst-case Robustness
A Characterization of List Learnability
Privacy Induces Robustness: Information-Computation Gaps and Sparse Mean Estimation
Is Out-of-Distribution Detection Learnable?
Learning versus Refutation in Noninteractive Local Differential Privacy
SQ Lower Bounds for Learning Single Neurons with Massart Noise
Superpolynomial Lower Bounds for Decision Tree Learning and Testing
Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond
Analyzing Robustness of Angluin's L* Algorithm in Presence of Noise
On PAC Learning Halfspaces in Non-interactive Local Privacy Model with Public Unlabeled Data
Fine-Grained Distribution-Dependent Learning Curves
Cryptographic Hardness of Learning Halfspaces with Massart Noise
Generalization Bounds for Data-Driven Numerical Linear Algebra
PAC Generalization via Invariant Representations
Bézier Flow: a Surface-wise Gradient Descent Method for Multi-objective Optimization
Sample Complexity Bounds for Robustly Learning Decision Lists against Evasion Attacks
VICE: Variational Interpretable Concept Embeddings
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.