Blum, Avrim

Noise-tolerant learning, the parity problem, and the statistical query model

Blum, A., Kalai, A., & Wasserman, H. (2003) · Journal of the ACM

Machine Learning and AlgorithmsComplexity and Algorithms in Graphs

Cited by 598

Beating the hold-out: bounds for K-fold and progressive cross-validation

Blum, A., Kalai, A., & Langford, J. (1999) · Proceedings of the twelfth annual conference on Computational learning theory

Machine Learning and AlgorithmsMachine Learning and Data Classification

Cited by 265

Noise-tolerant learning, the parity problem, and the statistical query model

Blum, A., Kalai, A., & Wasserman, H. (2000) · Proceedings of the thirty-second annual ACM symposium on Theory of computing

Machine Learning and AlgorithmsComplexity and Algorithms in Graphs

Cited by 128

Distributed Learning, Communication Complexity and Privacy

Balcan, M.-F., Blum, A., Fine, S., & Mansour, Y. (2012) · arXiv

Privacy-Preserving Technologies in DataMachine Learning and Algorithms

Cited by 117

The Ladder: A Reliable Leaderboard for Machine Learning Competitions

Blum, A., & Hardt, M. (2015) · arXiv

Machine Learning and Data ClassificationAdvanced Bandit Algorithms Research

Cited by 92

Recovering from Biased Data: Can Fairness Constraints Improve Accuracy?

Blum, A., & Stangl, K. (2019) · arXiv

Ethics and Social Impacts of AIPrivacy-Preserving Technologies in Data

Cited by 13