Follow
Daniel Russo
Daniel Russo
Verified email at gsb.columbia.edu - Homepage
Title
Cited by
Cited by
Year
A tutorial on thompson sampling
D Russo, B Van Roy, A Kazerouni, I Osband, Z Wen
Foundations and Trends in Machine Learning 11 (1), 1–96, 2018
12502018
Learning to optimize via posterior sampling
D Russo, B Van Roy
Mathematics of Operations Research 39 (4), 1221-1243, 2014
7882014
An information-theoretic analysis of thompson sampling
D Russo, B Van Roy
Journal of Machine Learning Research 17 (68), 1-30, 2016
4532016
A finite time analysis of temporal difference learning with linear function approximation
J Bhandari, D Russo, R Singal
Operations Research 69 (3), 950--973, 2021
4322021
How much does your data exploration overfit? Controlling bias via information usage.
D Russo, J Zou
IEEE Transactions on Information Theory, 2019
386*2019
Learning to optimize via information-directed sampling
D Russo, B Van Roy
Operations Research 66 (1), 230-252, 2018
363*2018
Deep exploration via randomized value functions
I Osband, B Van Roy, DJ Russo, Z Wen
Journal of Machine Learning Research 20 (124), 1-62, 2019
3572019
Simple Bayesian Algorithms for Best-Arm Identification
D Russo
Operations Research 68 (6), 1625--1647, 2020
339*2020
Eluder Dimension and the Sample Complexity of Optimistic Exploration.
D Russo, B Van Roy
Advances in Neural Information Processing Systems 26, 2256-2264, 2013
2872013
Global optimality guarantees for policy gradient methods
J Bhandari, D Russo
Operations Research, 2024
2792024
Improving the expected improvement algorithm
C Qin, D Klabjan, D Russo
Advances in Neural Information Processing Systems, 5382--5392, 2017
1702017
(More) efficient reinforcement learning via posterior sampling
I Osband, D Russo, B Van Roy
Advances in Neural Information Processing Systems 26, 2013
1122013
On the linear convergence of policy gradient methods for finite mdps
J Bhandari, D Russo
International Conference on Artificial Intelligence and Statistics, 2386-2394, 2021
107*2021
Worst-case regret bounds for exploration via randomized value functions
D Russo
Advances in Neural Information Processing Systems 32, 2019
972019
Satisficing in time-sensitive bandit learning
D Russo, B Van Roy
Mathematics of Operations Research 47 (4), 2815-2839, 2022
67*2022
Adaptive Experimentation in the Presence of Exogenous Nonstationary Variation
C Qin, D Russo
arXiv preprint arXiv:2202.09036, 2022
44*2022
A note on the equivalence of upper confidence bounds and gittins indices for patient agents
D Russo
Operations Research 69 (1), 273-278, 2021
182021
Impatient bandits: Optimizing recommendations for the long-term without delay
TM McDonald, L Maystre, M Lalmas, D Russo, K Ciosek
Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and …, 2023
152023
Policy gradient optimization of Thompson sampling policies
S Min, CC Moallemi, DJ Russo
arXiv preprint arXiv:2006.16507, 2020
132020
Approximation benefits of policy gradient methods with aggregated states
D Russo
Management Science 69 (11), 6898-6911, 2023
122023
The system can't perform the operation now. Try again later.
Articles 1–20