M. Kearns

发表

Bounds on the sample complexity of Bayesian learning using information theory and the VC dimension

David Haussler, Robert E. Schapire, Michael Kearns, 1991, COLT '91.

Algorithmic stability and sanity-check bounds for leave-one-out cross-validation

M. Kearns, D. Ron, 1999 .

On the learnability of Boolean formulae

Leslie G. Valiant, Leonard Pitt, Ming Li, 1987, STOC.

On the complexity of teaching

M. Kearns, S. Goldman, 1991, COLT '91.

Recent Results on Boolean Concept Learning

M. Kearns, Ming Li, L. Pitt, 1987 .

Learning in the presence of malicious errors

Ming Li, Michael Kearns, M. Kearns, 1993, STOC '88.

Equivalence of models for polynomial learnability

David Haussler, Manfred K. Warmuth, Michael Kearns, 1988, COLT '88.

A general lower bound on the number of examples needed for learning

Leslie G. Valiant, David Haussler, Andrzej Ehrenfeucht, 1988, COLT '88.

Approximate Planning in Large POMDPs via Reusable Trajectories

Yishay Mansour, Andrew Y. Ng, Michael Kearns, 1999, NIPS.

Rigorous learning curve bounds from statistical mechanics

D. Haussler, M. Kearns, H. Seung, 1996 .

Rigorous learning curve bounds from statistical mechanics

D. Haussler, M. Kearns, H. Seung, 1994, COLT '94.

Toward Efficient Agnostic Learning

R. Schapire, M. Kearns, Linda Sellie, 1994 .

Toward efficient agnostic learning

R. Schapire, M. Kearns, Linda Sellie, 1992, COLT '92.

Cryptographic Limitations on Learning Boolean Formulae and Finite Automata

Leslie G. Valiant, Michael Kearns, M. Kearns, 1993, Machine Learning: From Theory to Applications.

ON THE CONSEQUENCES OF THE STATISTICAL MECHANICS THEORY OF LEARNING CURVES FOR THE MODEL SELECTION PROBLEM

M. Kearns, .

Efficient distribution-free learning of probabilistic concepts

Robert E. Schapire, Michael Kearns, R. Schapire, 1990, Proceedings [1990] 31st Annual Symposium on Foundations of Computer Science.

Computational complexity of machine learning

Michael Kearns, M. Kearns, 1990, ACM distinguished dissertations.

A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov Decision Processes

Yishay Mansour, Andrew Y. Ng, Michael Kearns, 1999, Machine Learning.

Efficient Reinforcement Learning in Factored MDPs

Michael Kearns, Daphne Koller, M. Kearns, 1999, IJCAI.

A polynomial-time algorithm for learning k-variable pattern languages from examples

Leonard Pitt, Michael Kearns, M. Kearns, 1989, COLT '89.

Advances in neural information processing systems : proceedings of the ... conference

Thomas G. Dietterich, Richard P. Lippmann, Klaus-Robert Müller, 1989 .

Learning from a Population of Hypotheses

H. Sebastian Seung, Michael Kearns, M. Kearns, 1993, COLT '93.

Rigorous Learning Curve Bounds from Statistical Mechanics

David Haussler, H. Sebastian Seung, Naftali Tishby, 1994, COLT.

Fast Planning in Stochastic Games

Yishay Mansour, Michael Kearns, Satinder P. Singh, 2000, UAI.

On the Boosting Ability of Top-Down Decision Tree Learning Algorithms

Yishay Mansour, Michael Kearns, Y. Mansour, 1999, J. Comput. Syst. Sci..

Exact Identification of Read-Once Formulas Using Fixed Points of Amplification Functions

Robert E. Schapire, Michael Kearns, Sally A. Goldman, 1993, SIAM J. Comput..

A Bound on the Error of Cross Validation Using the Approximation and Estimation Rates, with Consequences for the Training-Test Split

Michael Kearns, M. Kearns, 1995, Neural Computation.

Efficient distribution-free learning of probabilistic concepts

Robert E. Schapire, Michael Kearns, R. Schapire, 1990, Proceedings [1990] 31st Annual Symposium on Foundations of Computer Science.

Toward efficient agnostic learning

Linda Sellie, Robert E. Schapire, Michael Kearns, 1992, COLT '92.

Cryptographic limitations on learning Boolean formulae and finite automata

Leslie G. Valiant, Michael Kearns, M. Kearns, 1994, JACM.

An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clustering

Yishay Mansour, Andrew Y. Ng, Michael Kearns, 1997, UAI.

On the boosting ability of top-down decision tree learning algorithms

Yishay Mansour, Michael Kearns, Y. Mansour, 1996, STOC '96.

An Introduction to Computational Learning Theory

Umesh V. Vazirani, Michael Kearns, M. Kearns, 1994 .

Applying the Waek Learning Framework to Understand and Improve C4.5

Thomas G. Dietterich, Yishay Mansour, Michael Kearns, 1996, ICML.

Efficient algorithms for learning to play repeated games against computationally bounded adversaries

Ronitt Rubinfeld, Dana Ron, Yishay Mansour, 1995, Proceedings of IEEE 36th Annual Foundations of Computer Science.

Bounds on the sample complexity of Bayesian learning using information theory and the VC dimension

R. Schapire, D. Haussler, M. Kearns, 1991, COLT '91.

Algorithmic Stability and Sanity-Check Bounds for Leave-One-Out Cross-Validation

Dana Ron, Michael Kearns, M. Kearns, 1997, Neural Computation.

Bounds on the sample complexity of Bayesian learning using information theory and the VC dimension

Michael Kearns, R. Schapire, D. Haussler, 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

Efficient noise-tolerant learning from statistical queries

Michael Kearns, M. Kearns, 1993, STOC.

Algorithmic Stability and Sanity-Check Bounds for Leave-one-Out Cross-Validation

Dana Ron, Michael Kearns, M. Kearns, 1997, COLT.

An experimental and theoretical comparison of model selection methods

Dana Ron, Yishay Mansour, Andrew Y. Ng, 1995, COLT '95.

An Experimental and Theoretical Comparison of Model Selection Methods

Dana Ron, Yishay Mansour, Andrew Y. Ng, 1995, COLT '95.

Learning Boolean Formulae

M. Kearns, 2022 .

On the complexity of teaching

Michael Kearns, Sally A. Goldman, M. Kearns, 1991, COLT '91.

A Fast, Bottom-Up Decision Tree Pruning Algorithm with Near-Optimal Generalization

Yishay Mansour, Michael Kearns, Y. Mansour, 1998, ICML.

Cryptographic Primitives Based on Hard Learning Problems

Richard J. Lipton, Avrim Blum, Michael Kearns, 1993, CRYPTO.

On the Sample Complexity of Weakly Learning

R. Schapire, M. Kearns, S. Goldman, 1992 .

Efficient Nash Computation in Large Population Games with Bounded Influence pdf

Yishay Mansour, Michael Kearns, Y. Mansour, 2002, UAI.

Large Deviation Methods for Approximate Probabilistic Inference pdf

Lawrence K. Saul, Michael Kearns, M. Kearns, 1998, UAI.

Horn Approximations of Empirical Data

Bart Selman, Henry A. Kautz, Michael Kearns, 1995, Artif. Intell..

On the Learnability of Discrete Distributions Extended Abstract

M. Kearns, 1994 .

Inference in Multilayer Networks Large Deviation Bounds

M. Kearns, L. Saul, 1998 .

Composition of Learning Models: Predicting with Distributions

Zhiwei Steven Wu, M. Kearns, 2016 .

livious ear ie

M. Kearns, 1992 .

On the sample complexity of weak learning

Robert E. Schapire, Michael Kearns, Sally A. Goldman, 1990, COLT '90.

Efficient noise-tolerant learning from statistical queries

M. Kearns, 1998, JACM.

Eecient Learning of Typical Finite Automata from Random Walks Extended Abstract

Y. Freund, M. Kearns, D. Ron, 1996 .

An Algorithm That Finds Truth Even If Most People Are Wrong

M. Kearns, S. Frederick, E. Maskin, 2007 .

Asymptotic Active Learning

Y. Mansour, M. Kearns, Eyal Even-Dar, 2007 .

Preface: the AAAI-02 conference

Rina Dechter, Michael Kearns, Rich Sutton, 2002, AAAI Conference on Artificial Intelligence.

Rigorous learning curve bounds from statistical mechanics

David Haussler, H. Sebastian Seung, Naftali Tishby, 1994, Machine-mediated learning.

Crytographic limitations on learning Boolean formulae and finite automata

M. Kearns, L. Valiant, 1989, STOC '89.

Advances in Neural Information Processing Systems 1, [NIPS Conference, Denver, Colorado, USA, 1988]

Michael I. Jordan, Sara A. Solla, Michael Kearns, 1989, NIPS.

Proof: Let N =

Y. Mansour, M. Kearns, L. Pitt, 1996 .

Toward Efficient Agnostic Learning

R. Schapire, M. Kearns, Linda Sellie, 1992, COLT.

Rigorous learning curve bounds from statistical mechanics

D. Haussler, M. Kearns, H. Seung, 1994, Machine Learning.

Toward efficient agnostic learning

Linda Sellie, Robert E. Schapire, Michael Kearns, 1992, Annual Conference Computational Learning Theory.

Exact identification of circuits using fixed points of amplification functions

R. Schapire, M. Kearns, S. Goldman, 1990, Proceedings [1990] 31st Annual Symposium on Foundations of Computer Science.

Proceedings of the workshop on Computational learning theory and natural learning systems (vol. 2) : intersections between theory and experiment: intersections between theory and experiment

Ronald L. Rivest, Stephen José Hanson, Thomas Petsche, 1994 .

Eighteenth national conference on Artificial intelligence

Rina Dechter, Rich Sutton, Michael J. Kearns, 2002 .

Private Synthetic Data for Multitask Learning and Marginal Queries

Zhiwei Steven Wu, M. Kearns, C. Archambeau, 2022, NeurIPS.

Efficient Distribution-Free Learning of Probabilistic

Robert E. Schapire, Michael Kearns, R. Schapire, 1994 .

The Vapnik-Chervonenkis Dimension

Umesh Vazirani, Michael Kearns, M. Kearns, 1994 .

The Probably Approximately Correct Learning Model

Umesh Vazirani, Michael Kearns, M. Kearns, 1994 .

Appendix: Some Tools for Probabilistic Analysis

Umesh Vazirani, Michael Kearns, M. Kearns, 1994 .

Exploration Strategies for Model-based Learning 37 Convergence Results for Single-step On-policy Reinforcement-learning Algorithms. Machine Learning Journal Exploration Strategies for Model-based Learning Exploration Strategies for Model-based Learning

Y. Mansour, Y. Freund, R. Schapire, 2007 .

An Algorithm That Finds Truth Even If Most People Are Wrong

M. Kearns, S. Frederick, E. Maskin, 2007 .

On the learnability of discrete distributions

Ronitt Rubinfeld, Dana Ron, Linda Sellie, 1994, STOC '94.

Testing problems with sub-learning sample complexity

Dana Ron, Michael Kearns, M. Kearns, 1998, COLT' 98.

Weakly learning DNF and characterizing statistical query learning using Fourier analysis

Yishay Mansour, Avrim Blum, Michael Kearns, 1994, STOC '94.

Exact identification of circuits using fixed points of amplification functions

Robert E. Schapire, Michael Kearns, Sally A. Goldman, 1990, Proceedings [1990] 31st Annual Symposium on Foundations of Computer Science.

Efficient learning of typical finite automata from random walks

Ronitt Rubinfeld, Dana Ron, Linda Sellie, 1993, STOC.

AI Model Disgorgement: Methods and Choices

M. Kearns, A. Achille, S. Soatto, 2023, ArXiv.

Computational Learning Theory

Umesh V. Vazirani, Michael Kearns, M. Kearns, 1995, SIGACT News.

On the Sample Complexity of Weakly Learning

Robert E. Schapire, Michael Kearns, Sally A. Goldman, 1995, Inf. Comput..

Inference in Multilayer Networks via Large Deviation Bounds

Lawrence K. Saul, Michael Kearns, M. Kearns, 1998, NIPS.

Reasoning With Characteristic Models

Bart Selman, Henry A. Kautz, Michael Kearns, 1993, AAAI.

Replicable Reinforcement Learning

M. Kearns, Eric Eaton, Marcel Hussing, 2023, ArXiv.

Boosting Theory Towards Practice: Recent Developments in Decision Tree Induction and the Weak Learning Framework

Michael Kearns, M. Kearns, 1996, AAAI/IAAI, Vol. 2.

The Minimal Disagreement Parity Problem as a Hard Satisfiability Problem

James M. Crawford, Robert E. Schapire, R. Schapire, 1995 .

Testing Problems with Sublearning Sample Complexity

Dana Ron, Michael Kearns, M. Kearns, 2000, J. Comput. Syst. Sci..

Bounds on the Sample Complexity of Bayesian Learning Using Information Theory and the VC Dimension

R. Schapire, D. Haussler, M. Kearns, 1991, Machine Learning.

A tutorial on theoretical issues in probabilistic artificial intelligence

M. Kearns, M. Kearns, 1998, Proceedings 39th Annual Symposium on Foundations of Computer Science (Cat. No.98CB36280).

Learning Boolean formulas

Leslie G. Valiant, Ming Li, Michael Kearns, 1994, JACM.

Oblivious PAC Learning of Concept Hierarchies

Michael Kearns, M. Kearns, 1992, AAAI.