Convex Analysis at Infinity: An Introduction to Astral Space
Miro Dudík, Robert E. Schapire, Matus Telgarsky
July 2024
Robert Schapire
Partner Researcher
Publications
Publications by Year
-
Provable Interactive Learning with Hindsight Instruction Feedback
Dipendra Misra, Aldo Pacchiano, Robert E. Schapire
ICML 2024 | April 2024
-
Contextual search in the presence of adversarial corruptions
Akshay Krishnamurthy, Thodoris Lykouris, Chara Podimata, Robert E. Schapire
Operations Research | November 2022
Provably sample-efficient RL with side information about latent dynamics
Yao Liu, Dipendra Misra, Miro Dudík, Robert E. Schapire
2022 Neural Information Processing Systems | May 2022
-
Bayesian decision-making under misspecified priors with applications to meta-learning
Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu, Thodoris Lykouris, Miro Dudík, Robert E. Schapire
NeurIPS 2021 | December 2021
Multiclass Boosting and the Cost of Weak Learning
Nataly Brukhim, Elad Hazan, Shay Moran, Robert E. Schapire
NeurIPS 2021 | December 2021
Interactive Learning from Activity Description
Khanh Nguyen, Dipendra Misra, Robert E. Schapire, Miro Dudík, Patrick Shafto
2021 International Conference on Machine Learning | July 2021
-
Gradient Descent Follows the Regularization Path for General Losses
Ziwei Ji, Miro Dudík, Robert E. Schapire, Matus Telgarsky
COLT 2020 | June 2020
-
On Oracle-Efficient PAC Reinforcement Learning with Rich Observations
Christoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
Advances in Neural Information Processing Systems | December 2018
Learning Deep ResNet Blocks Sequentially using Boosting Theory
Furon Huang, Jordan Ash, John Langford, Robert E. Schapire
ICML 2018 | July 2018
Practical Contextual Bandits with Regression Oracles
Dylan Foster, Alekh Agarwal, Miro Dudík, Haipeng Luo, Robert E. Schapire
International Conference on Machine Learning (ICML) | July 2018
International Conference on Machine Learning
-
Oracle-Efficient Learning and Auction Design
Miro Dudík, Nika Haghtalab, Haipeng Luo, Robert E. Schapire, Vasilis Syrgkanis, Jennifer Wortman Vaughan
Proceedings of the 58th Annual Symposium on Foundations of Computer Science (FOCS), 2017. | October 2017
Contextual Decision Processes with low Bellman rank are PAC-Learnable
Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
International Conference on Machine Learning | August 2017
Corralling a Band of Bandit Algorithms
Alekh Agarwal, Haipeng Luo, Behnam Neyshabur, Robert E. Schapire
Proceedings of the 2017 Conference on Learning Theory (COLT) | July 2017
Open Problem: First-Order Regret Bounds for Contextual Bandits
Alekh Agarwal, Akshay Krishnamurthy, John Langford, Haipeng Luo, Robert E. Schapire
Conference on Learning Theory | July 2017
-
Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits
Vasilis Syrgkanis, Haipeng Luo, Akshay Krishnamurthy, Robert E. Schapire
Advances in Neural Information Processing Systems | December 2016
Efficient Algorithms for Adversarial Contextual Learning
Vasilis Syrgkanis, Akshay Krishnamurthy, Robert E. Schapire
International Conference on Machine Learning | June 2016
Exploratory Gradient Boosting for Reinforcement Learning in Complex Domains
David Abel, Alekh Agarwal, Fernando Diaz, Akshay Krishnamurthy, Robert E. Schapire
ArXiv preprint | March 2016
-
Efficient and Parsimonious Agnostic Active Learning
Tzu-Kuo Huang, Alekh Agarwal, Daniel Hsu, John Langford, Robert E. Schapire
Advances in Neural Information Processing Systems 28 (NIPS 2015) | December 2015
Fast Convergence of Regularized Learning in Games
Vasilis Syrgkanis, Alekh Agarwal, Haipeng Luo, Robert E. Schapire
Advances in Neural Information Processing Systems 28 (NIPS 2015) | December 2015
Best Paper Award
Contextual Dueling Bandits
Miro Dudík, Katja Hofmann, Robert E. Schapire, Aleksandrs Slivkins, Masrour Zoghi
Proceedings of The 28th Conference on Learning Theory (COLT) | July 2015
Proceedings of The 28th Conference on Learning Theory (COLT)
-
Robust Multi-objective Learning with Mentor Feedback
Alekh Agarwal, Ashwinkumar Badanidiyuru, Miroslav Dudik, Robert E. Schapire, Aleksandrs Slivkins, Aleksandrs Slivkins, Miro Dudík
27th Conf. on Learning Theory (COLT) | July 2014
27th Conf. on Learning Theory (COLT)
Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
Alekh Agarwal, Daniel Hsu, Satyen Kale, John Langford, Lihong Li, Robert E. Schapire
The 31st International Conference on Machine Learning (ICML 2014) | June 2014
Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
Alekh Agarwal, Daniel Hus, Satyen Kale, John Langford, Lihong Li, Robert E. Schapire
MSR-TR-2014-33 | February 2014
-
Contextual bandit algorithms with supervised learning guarantees
Alina Beygelzimer, John Langford, Lihong Li, Lev Reyzin, Robert E. Schapire
AISTATS 2011 | October 2011
Contextual Bandits with Linear Payoff Functions
Wei Chu, Lihong Li, Lev Reyzin, Robert E. Schapire
AISTATS 2011 | April 2011
-
A contextual-bandit approach to personalized news article recommendation
Lihong Li, Wei Chu, John Langford, Robert E. Schapire
WWW 2010 | March 2010
2023 Seoul Test of Time Award
-
The Nonstochastic Multiarmed Bandit Problem
Peter Auer, Nicolò Cesa-Bianchi, Yoav Freund, Robert E. Schapire
SIAM Journal on Computing | October 2002, Vol 32(1): pp. 48-77
-
Contextual bandit learning with predictable rewards
Miro Dudík, Satyen Kale, John Langford, Alekh Agarwal, Robert E. Schapire
Proceedings of the 15th International Conference on Artificial Intelligence and Statistics (AISTATS-12) | January 2000
Publications by Research Area
-
Contextual bandit learning with predictable rewards
Miro Dudík, Satyen Kale, John Langford, Alekh Agarwal, Robert E. Schapire
Proceedings of the 15th International Conference on Artificial Intelligence and Statistics (AISTATS-12) | January 2000
Convex Analysis at Infinity: An Introduction to Astral Space
Miro Dudík, Robert E. Schapire, Matus Telgarsky
July 2024
Provable Interactive Learning with Hindsight Instruction Feedback
Dipendra Misra, Aldo Pacchiano, Robert E. Schapire
ICML 2024 | April 2024
Contextual search in the presence of adversarial corruptions
Akshay Krishnamurthy, Thodoris Lykouris, Chara Podimata, Robert E. Schapire
Operations Research | November 2022
Provably sample-efficient RL with side information about latent dynamics
Yao Liu, Dipendra Misra, Miro Dudík, Robert E. Schapire
2022 Neural Information Processing Systems | May 2022
Bayesian decision-making under misspecified priors with applications to meta-learning
Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu, Thodoris Lykouris, Miro Dudík, Robert E. Schapire
NeurIPS 2021 | December 2021
Multiclass Boosting and the Cost of Weak Learning
Nataly Brukhim, Elad Hazan, Shay Moran, Robert E. Schapire
NeurIPS 2021 | December 2021
Interactive Learning from Activity Description
Khanh Nguyen, Dipendra Misra, Robert E. Schapire, Miro Dudík, Patrick Shafto
2021 International Conference on Machine Learning | July 2021
Gradient Descent Follows the Regularization Path for General Losses
Ziwei Ji, Miro Dudík, Robert E. Schapire, Matus Telgarsky
COLT 2020 | June 2020
On Oracle-Efficient PAC Reinforcement Learning with Rich Observations
Christoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
Advances in Neural Information Processing Systems | December 2018
Learning Deep ResNet Blocks Sequentially using Boosting Theory
Furon Huang, Jordan Ash, John Langford, Robert E. Schapire
ICML 2018 | July 2018
Practical Contextual Bandits with Regression Oracles
Dylan Foster, Alekh Agarwal, Miro Dudík, Haipeng Luo, Robert E. Schapire
International Conference on Machine Learning (ICML) | July 2018
International Conference on Machine Learning
Oracle-Efficient Learning and Auction Design
Miro Dudík, Nika Haghtalab, Haipeng Luo, Robert E. Schapire, Vasilis Syrgkanis, Jennifer Wortman Vaughan
Proceedings of the 58th Annual Symposium on Foundations of Computer Science (FOCS), 2017. | October 2017
Contextual Decision Processes with low Bellman rank are PAC-Learnable
Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
International Conference on Machine Learning | August 2017
Open Problem: First-Order Regret Bounds for Contextual Bandits
Alekh Agarwal, Akshay Krishnamurthy, John Langford, Haipeng Luo, Robert E. Schapire
Conference on Learning Theory | July 2017
Corralling a Band of Bandit Algorithms
Alekh Agarwal, Haipeng Luo, Behnam Neyshabur, Robert E. Schapire
Proceedings of the 2017 Conference on Learning Theory (COLT) | July 2017
Efficient Algorithms for Adversarial Contextual Learning
Vasilis Syrgkanis, Akshay Krishnamurthy, Robert E. Schapire
International Conference on Machine Learning | June 2016
Exploratory Gradient Boosting for Reinforcement Learning in Complex Domains
David Abel, Alekh Agarwal, Fernando Diaz, Akshay Krishnamurthy, Robert E. Schapire
ArXiv preprint | March 2016
Efficient and Parsimonious Agnostic Active Learning
Tzu-Kuo Huang, Alekh Agarwal, Daniel Hsu, John Langford, Robert E. Schapire
Advances in Neural Information Processing Systems 28 (NIPS 2015) | December 2015
Fast Convergence of Regularized Learning in Games
Vasilis Syrgkanis, Alekh Agarwal, Haipeng Luo, Robert E. Schapire
Advances in Neural Information Processing Systems 28 (NIPS 2015) | December 2015
Best Paper Award
Contextual Dueling Bandits
Miro Dudík, Katja Hofmann, Robert E. Schapire, Aleksandrs Slivkins, Masrour Zoghi
Proceedings of The 28th Conference on Learning Theory (COLT) | July 2015
Proceedings of The 28th Conference on Learning Theory (COLT)
Robust Multi-objective Learning with Mentor Feedback
Alekh Agarwal, Ashwinkumar Badanidiyuru, Miroslav Dudik, Robert E. Schapire, Aleksandrs Slivkins, Aleksandrs Slivkins, Miro Dudík
27th Conf. on Learning Theory (COLT) | July 2014
27th Conf. on Learning Theory (COLT)
Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
Alekh Agarwal, Daniel Hsu, Satyen Kale, John Langford, Lihong Li, Robert E. Schapire
The 31st International Conference on Machine Learning (ICML 2014) | June 2014
Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
Alekh Agarwal, Daniel Hus, Satyen Kale, John Langford, Lihong Li, Robert E. Schapire
MSR-TR-2014-33 | February 2014
Contextual bandit algorithms with supervised learning guarantees
Alina Beygelzimer, John Langford, Lihong Li, Lev Reyzin, Robert E. Schapire
AISTATS 2011 | October 2011
Contextual Bandits with Linear Payoff Functions
Wei Chu, Lihong Li, Lev Reyzin, Robert E. Schapire
AISTATS 2011 | April 2011
A contextual-bandit approach to personalized news article recommendation
Lihong Li, Wei Chu, John Langford, Robert E. Schapire
WWW 2010 | March 2010
2023 Seoul Test of Time Award
The Nonstochastic Multiarmed Bandit Problem
Peter Auer, Nicolò Cesa-Bianchi, Yoav Freund, Robert E. Schapire
SIAM Journal on Computing | October 2002, Vol 32(1): pp. 48-77
-
Convex Analysis at Infinity: An Introduction to Astral Space
Miro Dudík, Robert E. Schapire, Matus Telgarsky
July 2024
-
Multiclass Boosting and the Cost of Weak Learning
Nataly Brukhim, Elad Hazan, Shay Moran, Robert E. Schapire
NeurIPS 2021 | December 2021
Oracle-Efficient Learning and Auction Design
Miro Dudík, Nika Haghtalab, Haipeng Luo, Robert E. Schapire, Vasilis Syrgkanis, Jennifer Wortman Vaughan
Proceedings of the 58th Annual Symposium on Foundations of Computer Science (FOCS), 2017. | October 2017
Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits
Vasilis Syrgkanis, Haipeng Luo, Akshay Krishnamurthy, Robert E. Schapire
Advances in Neural Information Processing Systems | December 2016
Efficient Algorithms for Adversarial Contextual Learning
Vasilis Syrgkanis, Akshay Krishnamurthy, Robert E. Schapire
International Conference on Machine Learning | June 2016
Robust Multi-objective Learning with Mentor Feedback
Alekh Agarwal, Ashwinkumar Badanidiyuru, Miroslav Dudik, Robert E. Schapire, Aleksandrs Slivkins, Aleksandrs Slivkins, Miro Dudík
27th Conf. on Learning Theory (COLT) | July 2014
27th Conf. on Learning Theory (COLT)
-
Oracle-Efficient Learning and Auction Design
Miro Dudík, Nika Haghtalab, Haipeng Luo, Robert E. Schapire, Vasilis Syrgkanis, Jennifer Wortman Vaughan
Proceedings of the 58th Annual Symposium on Foundations of Computer Science (FOCS), 2017. | October 2017
Publications by Type
-
Convex Analysis at Infinity: An Introduction to Astral Space
Miro Dudík, Robert E. Schapire, Matus Telgarsky
July 2024
-
Contextual bandit learning with predictable rewards
Miro Dudík, Satyen Kale, John Langford, Alekh Agarwal, Robert E. Schapire
Proceedings of the 15th International Conference on Artificial Intelligence and Statistics (AISTATS-12) | January 2000
Provable Interactive Learning with Hindsight Instruction Feedback
Dipendra Misra, Aldo Pacchiano, Robert E. Schapire
ICML 2024 | April 2024
Provably sample-efficient RL with side information about latent dynamics
Yao Liu, Dipendra Misra, Miro Dudík, Robert E. Schapire
2022 Neural Information Processing Systems | May 2022
Bayesian decision-making under misspecified priors with applications to meta-learning
Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu, Thodoris Lykouris, Miro Dudík, Robert E. Schapire
NeurIPS 2021 | December 2021
Multiclass Boosting and the Cost of Weak Learning
Nataly Brukhim, Elad Hazan, Shay Moran, Robert E. Schapire
NeurIPS 2021 | December 2021
Interactive Learning from Activity Description
Khanh Nguyen, Dipendra Misra, Robert E. Schapire, Miro Dudík, Patrick Shafto
2021 International Conference on Machine Learning | July 2021
Gradient Descent Follows the Regularization Path for General Losses
Ziwei Ji, Miro Dudík, Robert E. Schapire, Matus Telgarsky
COLT 2020 | June 2020
On Oracle-Efficient PAC Reinforcement Learning with Rich Observations
Christoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
Advances in Neural Information Processing Systems | December 2018
Learning Deep ResNet Blocks Sequentially using Boosting Theory
Furon Huang, Jordan Ash, John Langford, Robert E. Schapire
ICML 2018 | July 2018
Practical Contextual Bandits with Regression Oracles
Dylan Foster, Alekh Agarwal, Miro Dudík, Haipeng Luo, Robert E. Schapire
International Conference on Machine Learning (ICML) | July 2018
International Conference on Machine Learning
Oracle-Efficient Learning and Auction Design
Miro Dudík, Nika Haghtalab, Haipeng Luo, Robert E. Schapire, Vasilis Syrgkanis, Jennifer Wortman Vaughan
Proceedings of the 58th Annual Symposium on Foundations of Computer Science (FOCS), 2017. | October 2017
Contextual Decision Processes with low Bellman rank are PAC-Learnable
Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
International Conference on Machine Learning | August 2017
Open Problem: First-Order Regret Bounds for Contextual Bandits
Alekh Agarwal, Akshay Krishnamurthy, John Langford, Haipeng Luo, Robert E. Schapire
Conference on Learning Theory | July 2017
Corralling a Band of Bandit Algorithms
Alekh Agarwal, Haipeng Luo, Behnam Neyshabur, Robert E. Schapire
Proceedings of the 2017 Conference on Learning Theory (COLT) | July 2017
Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits
Vasilis Syrgkanis, Haipeng Luo, Akshay Krishnamurthy, Robert E. Schapire
Advances in Neural Information Processing Systems | December 2016
Efficient Algorithms for Adversarial Contextual Learning
Vasilis Syrgkanis, Akshay Krishnamurthy, Robert E. Schapire
International Conference on Machine Learning | June 2016
Efficient and Parsimonious Agnostic Active Learning
Tzu-Kuo Huang, Alekh Agarwal, Daniel Hsu, John Langford, Robert E. Schapire
Advances in Neural Information Processing Systems 28 (NIPS 2015) | December 2015
Fast Convergence of Regularized Learning in Games
Vasilis Syrgkanis, Alekh Agarwal, Haipeng Luo, Robert E. Schapire
Advances in Neural Information Processing Systems 28 (NIPS 2015) | December 2015
Best Paper Award
Contextual Dueling Bandits
Miro Dudík, Katja Hofmann, Robert E. Schapire, Aleksandrs Slivkins, Masrour Zoghi
Proceedings of The 28th Conference on Learning Theory (COLT) | July 2015
Proceedings of The 28th Conference on Learning Theory (COLT)
Robust Multi-objective Learning with Mentor Feedback
Alekh Agarwal, Ashwinkumar Badanidiyuru, Miroslav Dudik, Robert E. Schapire, Aleksandrs Slivkins, Aleksandrs Slivkins, Miro Dudík
27th Conf. on Learning Theory (COLT) | July 2014
27th Conf. on Learning Theory (COLT)
Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
Alekh Agarwal, Daniel Hsu, Satyen Kale, John Langford, Lihong Li, Robert E. Schapire
The 31st International Conference on Machine Learning (ICML 2014) | June 2014
Contextual bandit algorithms with supervised learning guarantees
Alina Beygelzimer, John Langford, Lihong Li, Lev Reyzin, Robert E. Schapire
AISTATS 2011 | October 2011
Contextual Bandits with Linear Payoff Functions
Wei Chu, Lihong Li, Lev Reyzin, Robert E. Schapire
AISTATS 2011 | April 2011
A contextual-bandit approach to personalized news article recommendation
Lihong Li, Wei Chu, John Langford, Robert E. Schapire
WWW 2010 | March 2010
2023 Seoul Test of Time Award
-
Contextual search in the presence of adversarial corruptions
Akshay Krishnamurthy, Thodoris Lykouris, Chara Podimata, Robert E. Schapire
Operations Research | November 2022
Exploratory Gradient Boosting for Reinforcement Learning in Complex Domains
David Abel, Alekh Agarwal, Fernando Diaz, Akshay Krishnamurthy, Robert E. Schapire
ArXiv preprint | March 2016
The Nonstochastic Multiarmed Bandit Problem
Peter Auer, Nicolò Cesa-Bianchi, Yoav Freund, Robert E. Schapire
SIAM Journal on Computing | October 2002, Vol 32(1): pp. 48-77
-
Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
Alekh Agarwal, Daniel Hus, Satyen Kale, John Langford, Lihong Li, Robert E. Schapire
MSR-TR-2014-33 | February 2014