Sotabase

Career

· Senior Principal Researcher, Microsoft2012–
· Research Scientist, Yahoo!2010–2012
· Postdoctoral Researcher, Carnegie Mellon University2007–2010
· Research Intern, IBM Research, Yorktown Heights2004–2004
· PhD, Computer Science, Princeton University2002–2007
· BS, Engineering and Applied Science, Caltech1999–2002
· Computer Science, Univerzita Komenského v Bratislave1997–1999

Publications (50)

A statistical explanation of MaxEnt for ecologists
2011
5,745
cited
Opening the black box: an open-source release of Maxent
2017
2,306
cited
A Reductions Approach to Fair Classification
International Conference on Machine Learning · 2018
1,215
cited
Improving Fairness in Machine Learning Systems: What Do Industry Practitioners Need?
International Conference on Human Factors in Computing Systems · 2018
909
cited
A reliable effective terascale linear learning system
Journal of machine learning research · 2011
424
cited
Fairlearn: A toolkit for assessing and improving fairness in AI
2020
419
cited
Efficient Optimal Learning for Contextual Bandits
Conference on Uncertainty in Artificial Intelligence · 2011
316
cited
Doubly Robust Policy Evaluation and Optimization
arXiv.org · 2014
304
cited
Fair Regression: Quantitative Definitions and Reduction-based Algorithms
2019
289
cited
Off-policy evaluation for slate recommendation
Neural Information Processing Systems · 2016
244
cited
Provably efficient RL with Rich Observations via Latent State Decoding
International Conference on Machine Learning · 2019
242
cited
Optimal and Adaptive Off-policy Evaluation in Contextual Bandits
2016
231
cited
Hierarchical Imitation and Reinforcement Learning
International Conference on Machine Learning · 2018
208
cited
Contextual Dueling Bandits
2015
145
cited
Practical Contextual Bandits with Regression Oracles
2018
135
cited
Doubly robust off-policy evaluation with shrinkage
2019
122
cited
Lifted coordinate descent for learning with trace-norm regularization
2012
116
cited
Large-scale image classification with trace-norm regularization
2012
112
cited
Reinforcement Learning with Convex Constraints
Neural Information Processing Systems · 2019
97
cited
Contextual Bandit Learning with Predictable Rewards
International Conference on Artificial Intelligence and Statistics · 2012
95
cited
Sotabase
Miroslav Dudík | Researcher Profile | Sotabase | Sotabase