Miroslav Dudík

21 papers · 2007–2025 · 6 conferences · across top CS/AI conferences

Achievements

+10 more ↓

🌉 Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🗺️ Taxonomy Completionist (12) 🧭 Keyword Pioneer 🌍 Conference Polyglot (6)

🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (6) 🌱 Topic Pioneer 🏆 Keyword Champion 🗃️ Keyword Collector (101) 📈 Trend Setter 💎 Century Club (21) 🔥 Unstoppable (8) 🚀 Conference Pioneer

Conferences

ICML (8) COLT (5) JMLR (3) AISTATS (2) NIPS (2) SEMEVAL (1)

Top co-authors

Alekh Agarwal (8) John Langford (5) Robert Schapire (5) Robert E. Schapire (4) Nan Jiang (2) Akshay Krishnamurthy (2) Matus Telgarsky (2) Aleksandrs Slivkins (2) Steven J. Phillips (2) Jérôme Malick (1)

Keywords

contextual bandit (4) regret bound (4) online learning (2) imitation learning (2) reinforcement learning (2) convex optimization (2) off-policy evaluation (1) multi-task learning (1) stochastic optimization (1) sequential decision-making (1) interactive learning (1) binary classification (1) maximum entropy (1) large-scale optimization (1) sample efficiency (1) density estimation (1) decision making (1) matrix factorization (1) sequential decision making (1) algorithmic fairness (1)

Papers

On the Hardness of Bandit Learning COLT 2025 SureMap: Simultaneous mean estimation for single-task and multi-task disaggregated evaluation NIPS 2024 Fairlearn: Assessing and Improving Fairness of AI Systems JMLR 2023 Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning ICML 2022 Interactive Learning from Activity Description ICML 2021 Doubly robust off-policy evaluation with shrinkage ICML 2020 Gradient descent follows the regularization path for general losses COLT 2020 Provably efficient RL with Rich Observations via Latent State Decoding ICML 2019 Fair Regression: Quantitative Definitions and Reduction-Based Algorithms ICML 2019 A Reductions Approach to Fair Classification ICML 2018 Practical Contextual Bandits with Regression Oracles ICML 2018 Hierarchical Imitation and Reinforcement Learning ICML 2018 Convex Risk Minimization and Conditional Probability Estimation COLT 2015 Contextual Dueling Bandits COLT 2015 A Reliable Effective Terascale Linear Learning System JMLR 2014 Robust Multi-objective Learning with Mentor Feedback COLT 2014 Lifted coordinate descent for learning with trace-norm regularization AISTATS 2012 Contextual Bandit Learning with Predictable Rewards AISTATS 2012 Generative and Discriminative Learning with Unknown Labeling Bias NIPS 2008 Maximum Entropy Density Estimation with Generalized Regularization and an Application to Species Distribution Modeling JMLR 2007 PU-BCD: Exponential Family Models for the Coarse- and Fine-Grained All-Words Tasks SEMEVAL 2007