World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
30
Citations
36427
World Ranking
13795
National Ranking
5471

Overview

Miroslav Dudík is affiliated with Microsoft in the United States and focuses primarily on the field of computer science. Their research has a strong emphasis on artificial intelligence, with significant contributions also in management science and operations research, management information systems, computer science applications, and computer networks and communications.

The scientist's research topics span several areas including advanced bandit algorithms research, machine learning and algorithms, reinforcement learning in robotics, stochastic gradient optimization techniques, adversarial robustness in machine learning, data stream mining techniques, and big data and business intelligence.

Among their recent publications are:

  • "Fairlearn: Assessing and Improving Fairness of AI Systems" (2023), published in arXiv (Cornell University)
  • "Constrained episodic reinforcement learning in concave-convex and knapsack settings" (2020), published in arXiv (Cornell University)
  • "Bayesian decision-making under misspecified priors with applications to meta-learning" (2021), published in arXiv (Cornell University)
  • "Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning" (2022), published in arXiv (Cornell University)
  • "Gradient descent follows the regularization path for general losses" (2020), published in arXiv (Cornell University)

The scientist's frequent co-authors include Robert E. Schapire, Thodoris Lykouris, Max Simchowitz, Ziwei Ji, and Matus Telgarsky. Dudík has published in venues such as arXiv (Cornell University), Communications of the ACM, and the 2022 ACM Conference on Fairness, Accountability, and Transparency.

Best Publications

  • Modeling of species distributions with Maxent: new extensions and a comprehensive evaluation

    Steven J. Phillips;Miroslav Dudík

  • A statistical explanation of MaxEnt for ecologists

    Jane Elith;Steven J. Phillips;Trevor Hastie;Miroslav Dudík

  • A maximum entropy approach to species distribution modeling

    Steven J. Phillips;Miroslav Dudík;Robert E. Schapire

  • Opening the black box: an open-source release of Maxent

    Steven J. Phillips;Robert P. Anderson;Robert P. Anderson;Miroslav Dudík;Robert E. Schapire

  • A Reductions Approach to Fair Classification

    Alekh Agarwal;Alina Beygelzimer;Miroslav Dudík;John Langford

  • Doubly Robust Policy Evaluation and Learning

    Miroslav Dudik;John Langford;Lihong Li

  • Modeling of species distributions with Maxent: new extensions and a comprehensive evaluation

    Unknown

  • A reliable effective terascale linear learning system

    Alekh Agarwal;Olivier Chapelle;Miroslav Dudík;John Langford

  • Doubly robust policy evaluation and optimization

    Miroslav Dudík;Dumitru Erhan;John Langford;Lihong Li

  • Correcting sample selection bias in maximum entropy density estimation

    Miroslav Dudík;Steven J. Phillips;Robert E Schapire

  • Maximum Entropy Density Estimation with Generalized Regularization and an Application to Species Distribution Modeling

    Miroslav Dudík;Steven J. Phillips;Robert E. Schapire

  • Efficient optimal learning for contextual bandits

    Miroslav Dudik;Daniel Hsu;Satyen Kale;Nikos Karampatziakis

  • A Reductions Approach to Fair Classification

    Alekh Agarwal;Alina Beygelzimer;Miroslav Dudík;John Langford

  • Off-policy evaluation for slate recommendation

    Adith Swaminathan;Akshay Krishnamurthy;Alekh Agarwal;Miroslav Dudík

  • Efficient Optimal Learning for Contextual Bandits

    Miroslav Dudik;Daniel Hsu;Satyen Kale;Nikos Karampatziakis

  • Lifted coordinate descent for learning with trace-norm regularization

    Miroslav Dudík;Zaïd Harchaoui;Jérôme Malick

  • Optimal and adaptive off-policy evaluation in contextual bandits

    Yu-Xiang Wang;Alekh Agarwal;Miroslav Dudík

  • Large-scale image classification with trace-norm regularization

    Zaid Harchaoui;Matthijs Douze;Mattis Paulin;Miroslav Dudik

  • Reconstruction from subsequences

    Miroslav Dudík;Leonard J. Schulman

  • Provably efficient RL with Rich Observations via Latent State Decoding

    Simon S. Du;Akshay Krishnamurthy;Nan Jiang;Alekh Agarwal

  • Fair regression: Quantitative definitions and reduction-based algorithms

    Alekh Agarwal;Miroslav Dudík;Zhiwei Steven Wu

  • Hierarchical imitation and reinforcement learning

    Hoang Minh Le;Nan Jiang;Alekh Agarwal;Miroslav Dudík

  • A Reliable Effective Terascale Linear Learning System

    Alekh Agarwal;Olivier Chapelle;Miroslav Dudik;John Langford

  • Maximum entropy distribution estimation with generalized regularization

    Miroslav Dudík;Robert E. Schapire

  • Practical Contextual Bandits with Regression Oracles

    Dylan J. Foster;Alekh Agarwal;Miroslav Dudík;Haipeng Luo

  • Fair Regression: Quantitative Definitions and Reduction-based Algorithms

    Alekh Agarwal;Miroslav Dudík;Zhiwei Steven Wu

  • Reinforcement learning with convex constraints

    Sobhan Miryoosefi;Kianté Brantley;Hal Daumé;Miroslav Dudík

Frequent Co-Authors

Robert E. Schapire
Robert E. Schapire Microsoft (United States)
Alekh Agarwal
Alekh Agarwal Google (United States)
John Langford
John Langford Microsoft (United States)
Akshay Krishnamurthy
Akshay Krishnamurthy Microsoft (United States)
Hal Daumé
Hal Daumé University of Maryland, College Park
Aleksandrs Slivkins
Aleksandrs Slivkins Microsoft (United States)
Geoffrey J. Gordon
Geoffrey J. Gordon Carnegie Mellon University
Lihong Li
Lihong Li Amazon (United States)
Satyen Kale
Satyen Kale Google (United States)
Dumitru Erhan
Dumitru Erhan Google (United States)

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

If you’re considering a degree in computer science, there are several related fields and career pathways that can be accessed through online programs. Many universities now offer affordable, accredited online degrees designed to help you develop practical, in-demand skills from home.

For example, students curious about engineering roles may want to explore an online degree for mechanical engineering or even an online bachelor’s in electrical engineering. These programs can lead to careers in manufacturing, robotics, energy, and beyond.

A strong foundation in mathematics and analytical thinking is also built through programs like an online physics bachelor's degree. Alternatively, students interested in analytics, machine learning, or AI should consider the most data science programs in the USA. Each of these fields complements computer science and offers broad career opportunities in today’s tech-driven world.

Best Scientists Citing Miroslav Dudík

Trending Scientists

Recently Published Articles