Dylan J. Foster
Dylan J. Foster
Postdoctoral Fellow, MIT
Verified email at mit.edu - Homepage
Title
Cited by
Cited by
Year
Spectrally-normalized margin bounds for neural networks
P Bartlett, DJ Foster, M Telgarsky
arXiv preprint arXiv:1706.08498, 2017
6072017
Learning in games: Robustness of fast convergence
DJ Foster, Z Li, T Lykouris, K Sridharan, E Tardos
Advances In Neural Information Processing Systems, 4734-4742, 2016
732016
Lower bounds for non-convex stochastic optimization
Y Arjevani, Y Carmon, JC Duchi, DJ Foster, N Srebro, B Woodworth
arXiv preprint arXiv:1912.02365, 2019
702019
Orthogonal statistical learning
DJ Foster, V Syrgkanis
arXiv preprint arXiv:1901.09036, 2019
502019
Naive exploration is optimal for online lqr
M Simchowitz, D Foster
International Conference on Machine Learning, 8937-8948, 2020
452020
Practical contextual bandits with regression oracles
D Foster, A Agarwal, M Dudik, H Luo, R Schapire
International Conference on Machine Learning, 1539-1548, 2018
402018
Logistic regression: The importance of being improper
DJ Foster, S Kale, H Luo, M Mohri, K Sridharan
Conference On Learning Theory, 167-208, 2018
352018
Parameter-free online learning via model selection
DJ Foster, S Kale, M Mohri, K Sridharan
arXiv preprint arXiv:1801.00101, 2017
342017
Adaptive online learning
DJ Foster, A Rakhlin, K Sridharan
arXiv preprint arXiv:1508.05170, 2015
342015
Uniform convergence of gradients for non-convex learning and optimization
DJ Foster, A Sekhari, K Sridharan
arXiv preprint arXiv:1810.11059, 2018
312018
Model selection for contextual bandits
DJ Foster, A Krishnamurthy, H Luo
arXiv preprint arXiv:1906.00531, 2019
302019
Beyond UCB: Optimal and efficient contextual bandits with regression oracles
D Foster, A Rakhlin
International Conference on Machine Learning, 3199-3210, 2020
282020
Logarithmic regret for adversarial online control
D Foster, M Simchowitz
International Conference on Machine Learning, 3211-3221, 2020
202020
The Complexity of Making the Gradient Small in Stochastic Convex Optimization
DJ Foster, A Sekhari, O Shamir, N Srebro, K Sridharan, B Woodworth
arXiv preprint arXiv:1902.04686, 2019
202019
Distributed learning with sublinear communication
J Acharya, C De Sa, D Foster, K Sridharan
International Conference on Machine Learning, 40-50, 2019
182019
Online learning: Sufficient statistics and the burkholder method
DJ Foster, A Rakhlin, K Sridharan
Conference On Learning Theory, 3028-3064, 2018
162018
Learning nonlinear dynamical systems from a single trajectory
D Foster, T Sarkar, A Rakhlin
Learning for Dynamics and Control, 851-861, 2020
132020
Instance-dependent complexity of contextual bandits and reinforcement learning: A disagreement-based perspective
DJ Foster, A Rakhlin, D Simchi-Levi, Y Xu
arXiv preprint arXiv:2010.03104, 2020
122020
Independent policy gradient methods for competitive reinforcement learning
C Daskalakis, DJ Foster, N Golowich
arXiv preprint arXiv:2101.04233, 2021
102021
Adapting to Misspecification in Contextual Bandits
DJ Foster, C Gentile, M Mohri, J Zimmert
Advances in Neural Information Processing Systems 33, 2020
102020
The system can't perform the operation now. Try again later.
Articles 1–20