Skip to main content

Avrim Blum

Professor, School of Computer Science


Avrim Blum

Research Areas

Privacy Protection

Cross Cutting Thrusts

Usable Privacy and Security


Avrim Blum is a Professor at the School of Computer Science. His main research interests are in the theoretical foundations of machine learning and data mining, in algorithmic game theory (including the design of incentive-compatible mechanisms for resource allocation), and in developing theoretical guarantees for privacy protection. He has served as Program Chair for the IEEE Symposium on Foundations of Computer Science (FOCS) and the Conference on Learning Theory (COLT). He was recipient of the Sloan Fellowship, the NSF National Young Investigator Award, the ICML/COLT 10-year best paper award, and the Herbert Simon Teaching Award, and he is a Fellow of the ACM.

His home department is the CMU Computer Science Department, but he is also affiliated with the CMU Machine Learning Department. He is additionally a member of the CS Theory Group.

His home page can be accessed at

Research Projects

Differentially-Private Synthetic Dataset Release for Machine Learning and Clustering

Research Area: Privacy Protection
Cross Cutting Thrusts: Usable Privacy and Security
Researcher: Avrim Blum

Applying Computational Learning Theory

Researcher: Avrim Blum


"Privacy-Preserving Public Information for Sequential Games". Avrim Blum, Jamie Morgenstern, Ankit Sharma, Adam Smith, ITCS 2015.

"Learning Valuation Distributions from Partial Observation". Avrim BlumYishay MansourJamie Morgenstern. AAAI 2015.

"Active Learning and Best-Response Dynamics". Nina Balcan, Chris Berlind, Emma Cohen, Kaushik Patnaik, and Le Song. Proc. 27th Annual Conference on Neural Information Processing Systems (NIPS) 2014.

"Learning Mixtures of Ranking Models". Pranjal Awasthi, Or Sheffet, and Aravindan Vijayaraghavan. Proc. 27th Annual Conference on Neural Information Processing Systems (NIPS) 2014.

"Learning Optimal Commitment to Overcome Insecurity". Nika Haghtalab and Ariel Procaccia. Proc. 27th Annual Conference on Neural Information Processing Systems (NIPS) 2014. 

"Lazy Defenders Are Almost Optimal Against Diligent Attackers". Nika Haghtalab and Ariel Procaccia. Proc. 28th AAAI Conference on Artificial Intelligence (AAAI), 2014.

"Estimating Accuracy from Unlabeled Data". Anthony Platanios (lead author) and Tom Mitchell. UAI 2014.

"Differentially Private Data Analysis of Social Networks via Restricted Sensitivity". Blocki, J., Blum, A., Datta, A., & Sheffet, O. (2013). 4th Innocations in Theoretical Computer Science Conference.

"Center-based Clustering under Perturbation Stability". Pranjal Awasthi and Or Sheffet. Information Processing Letters, 112(1-2):49-54, Jan 2012.

"Welfare and Profit Maximization with Production Costs". Anupam Gupta, Yishay Mansour, and Ankit Sharma. FOCS, 2011.

"A Discriminative Model for Semi-Supervised Learning". Nina Balcan. JACM Vol 57, Issue 3, 2010.

"Trading off Mistakes and Don't-Know Predictions". Amin Sayedi and Morteza Zadimoghaddam. NIPS 2010.