MD
Miroslav Dudík
cs.LGstat.MLcs.AIcs.GTmath.OCstat.APcs.CYcs.DScancer biologyCell Proliferation
On Valency
published · living versionsW_hktak6f3·v1 · currentpublished
Off-policy evaluation for slate recommendation
with Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal, John Langford +2
1 version
Preprints & journals
45 papers in the corpus · 2007–2026Use and Effects of LLMs in Peer Review: A Randomized Experiment and Survey at ICML 20262609.19420v1 · Sunnie S. Y. Kim, Wesley Hanwen Deng, Jennifer Wortman Vaughan et al.2026 · 0 citationsarXiv
Learning to Reason with Curriculum II: Compositional Generalization2606.27721v1 · Nived Rajaraman, Audrey Huang, Miroslav Dudik et al.2026 · 0 citationsarXiv
Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum2603.18325v2 · Nived Rajaraman, Audrey Huang, Miro Dudik et al.2026 · 0 citationsarXiv
Trade-offs in Ensembling, Merging and Routing Among Parameter-Efficient Experts2603.03535v1 · Sanae Lotfi, Lucas Caccia, Alessandro Sordoni et al.2026 · 0 citationsarXiv
On the Hardness of Bandit Learning2506.14746v1 · Nataly Brukhim, Aldo Pacchiano, Miroslav Dudik et al.2025 · 0 citationsarXiv
SureMap: Simultaneous Mean Estimation for Single-Task and Multi-Task Disaggregated Evaluation2411.09730v1 · Mikhail Khodak, Lester Mackey, Alexandra Chouldechova et al.2024 · 1 citationarXiv
A structured regression approach for evaluating model performance across intersectional subgroups2401.14893v2 · Christine Herlihy, Kimberly Truong, Alexandra Chouldechova et al.2024 · 5 citationsarXiv
Fairlearn: Assessing and Improving Fairness of AI Systems2303.16626v1 · Hilde Weerts, Miroslav Dud'ik, Richard Edgar et al.2023 · 47 citationsarXiv
Provably Sample-Efficient RL with Side Information about Latent Dynamics2205.14237v1 · Yao Liu, Dipendra Misra, Miro Dud'ik et al.2022 · 0 citationsarXiv
Astral Space: Convex Analysis at Infinity2205.03260v4 · Miroslav Dud'ik, Robert E. Schapire, Matus Telgarsky2022 · 0 citationsarXiv
Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning2202.05318v2 · Alberto Bietti, Chen-Yu Wei, Miroslav Dud'ik et al.2022 · 24 citationsarXiv
Interdisciplinarity, Gender Diversity, and Network Structure Predict the Centrality of AI Organizationsdp3ef_v1 · Madalina Vlasceanu, Miroslav Dudik, Ida Momennejad2021 · 3 citationsPsyArXiv
Bayesian decision-making under misspecified priors with applications to meta-learning2107.01509v1 · Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy et al.2021 · 9 citationsarXiv
Log-time Prediction Markets for Interval Securities2102.07308v2 · Miroslav Dud'ik, Xintong Wang, David M. Pennock et al.2021 · 2 citationsarXiv
Gradient descent follows the regularization path for general losses2006.11226v1 · Ziwei Ji, Miroslav Dud'ik, Robert E. Schapire et al.2020 · 14 citationsarXiv
Constrained episodic reinforcement learning in concave-convex and knapsack settings2006.05051v2 · Kiant'e Brantley, Miroslav Dudik, Thodoris Lykouris et al.2020 · 15 citationsarXiv
Doubly robust off-policy evaluation with shrinkage1907.09623v2 · Yi Su, Maria Dimakopoulou, Akshay Krishnamurthy et al.2019 · 31 citationsInternational Conference on Machine Learning (2020)
Reinforcement Learning with Convex Constraints1906.09323v2 · Sobhan Miryoosefi, Kiant'e Brantley, Hal Daum'e III et al.2019 · 48 citationsAdvances in Neural Information Processing Systems 32 (2019), 14093-14102
Fair Regression: Quantitative Definitions and Reduction-based Algorithms1905.12843v1 · Alekh Agarwal, Miroslav Dud'ik, Zhiwei Steven Wu2019 · 112 citationsarXiv
Provably efficient RL with Rich Observations via Latent State Decoding1901.09018v3 · Simon S. Du, Akshay Krishnamurthy, Nan Jiang et al.2019 · 67 citationsarXiv
A multifactorial model of T cell expansion and durable clinical benefit in response to a PD-L1 inhibitor.30596661 · Leiserson, Mark D M, Syrgkanis, Vasilis, Gilson, Amy et al.2019 · 16 citationsPloS one. 2018;13(12):e0208422
A Reductions Approach to Fair Classification1803.02453v3 · Alekh Agarwal, Alina Beygelzimer, Miroslav Dud'ik et al.2018 · 364 citationsarXiv
Practical Contextual Bandits with Regression Oracles1803.01088v1 · Dylan J. Foster, Alekh Agarwal, Miroslav Dud'ik et al.2018 · 45 citationsarXiv
Hierarchical Imitation and Reinforcement Learning1803.00590v2 · Hoang M. Le, Nan Jiang, Alekh Agarwal et al.2018 · 95 citationsarXiv
A Decomposition of Forecast Error in Prediction Markets1702.07810v2 · Miroslav Dud'ik, S'ebastien Lahaie, Ryan Rogers et al.2017 · 4 citationsAdvances in Neural Information Processing Systems 30 (NIPS 2017)
Optimal and Adaptive Off-policy Evaluation in Contextual Bandits1612.01205v2 · Yu-Xiang Wang, Alekh Agarwal, Miroslav Dudik2016 · 92 citationsInternational Conference on Machine Learning (pp. 3589-3597) (2017)on Valency
Oracle-Efficient Online Learning and Auction Design1611.01688v3 · Miroslav Dud'ik, Nika Haghtalab, Haipeng Luo et al.2016 · 30 citationsarXiv
Arbitrage-Free Combinatorial Market Making via Integer Programming1606.02825v2 · Christian Kroer, Miroslav Dud'ik, S'ebastien Lahaie et al.2016 · 2 citationsarXiv
Off-policy evaluation for slate recommendation1605.04812v3 · Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal et al.2016 · 58 citationsarXivon Valency
Budget Constraints in Prediction Markets1510.02045v1 · Nikhil Devanur, Miroslav Dud'ik, Zhiyi Huang et al.2015 · 0 citationsIn Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence, pages 238-247, 2015
Convex Risk Minimization and Conditional Probability Estimation1506.04513v1 · Matus Telgarsky, Miroslav Dud'ik, Robert Schapire2015 · 5 citationsarXiv
Doubly Robust Policy Evaluation and Optimization1503.02834v1 · Miroslav Dud'ik, Dumitru Erhan, John Langford et al.2015 · 210 citationsStatistical Science 2014, Vol. 29, No. 4, 485-511
Contextual Dueling Bandits1502.06362v2 · Miroslav Dud'ik, Katja Hofmann, Robert E. Schapire et al.2015 · 21 citationsarXiv
Contextual Semibandits via Supervised Learning Oracles1502.05890v4 · Akshay Krishnamurthy, Alekh Agarwal, Miroslav Dudik2015 · 6 citationsarXiv
Market Making with Decreasing Utility for Information1407.8161v1 · Miroslav Dud'ik, Rafael Frongillo, Jennifer Wortman Vaughan2014 · 1 citationM. Dudik, R. Frongillo, and J. Wortman Vaughan. Market Making with Decreasing Utility for Information. In Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence, pages 152-161, 2014
Para-active learning1310.8243v1 · Alekh Agarwal, Leon Bottou, Miroslav Dudik et al.2013 · 4 citationsarXiv
Sample-efficient Nonstationary Policy Evaluation for Contextual Bandits1210.4862v1 · Miroslav Dudik, Dumitru Erhan, John Langford et al.2012 · 18 citationsarXiv
First-Order Mixed Integer Linear Programming1205.2644v1 · Geoffrey Gordon, Sue Ann Hong, Miroslav Dudik2012 · 22 citationsarXiv
A Sampling-Based Approach to Computing Equilibria in Succinct Extensive-Form Games1205.2649v1 · Miroslav Dudik, Geoffrey Gordon2012 · 19 citationsarXiv
Contextual Bandit Learning with Predictable Rewards1202.1334v2 · Alekh Agarwal, Miroslav Dud'ik, Satyen Kale et al.2012 · 43 citationsarXivon Valency
A Reliable Effective Terascale Linear Learning System1110.4198v3 · Alekh Agarwal, Olivier Chapelle, Miroslav Dudik et al.2011 · 280 citationsarXiv
Efficient Optimal Learning for Contextual Bandits1106.2369v1 · Miroslav Dudik, Daniel Hsu, Satyen Kale et al.2011 · 174 citationsarXiv
Doubly Robust Policy Evaluation and Learning1103.4601v2 · Miroslav Dudik, John Langford, Lihong Li2011 · 383 citationsarXivon Valency
Sample selection bias and presence-only distribution models: implications for background and pseudo-absence data.19323182 · Phillips, Steven J, Dudík, Miroslav, Elith, Jane et al.2009 · 2,993 citationsEcological applications : a publication of the Ecological Society of America. 2009;19(1):181-97
Faster solutions of the inverse pairwise Ising problem0712.2437v2 · Tamara Broderick, Miroslav Dudik, Gasper Tkacik et al.2007 · 60 citationsarXiv
Career total: 98 works. 45 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.