Prati
Julian Zimmert
Julian Zimmert
Potvrđena adresa e-pošte na google.com
Naslov
Citirano
Citirano
Godina
An optimal algorithm for stochastic and adversarial bandits
J Zimmert, Y Seldin
The 22nd International Conference on Artificial Intelligence and Statistics …, 2019
1122019
Tsallis-inf: An optimal algorithm for stochastic and adversarial bandits
J Zimmert, Y Seldin
Journal of Machine Learning Research 22 (28), 1-49, 2021
1022021
Adapting to misspecification in contextual bandits
DJ Foster, C Gentile, M Mohri, J Zimmert
Advances in Neural Information Processing Systems 33, 11478-11489, 2020
862020
Model selection in contextual stochastic bandit problems
A Pacchiano, M Phan, Y Abbasi Yadkori, A Rao, J Zimmert, T Lattimore, ...
Advances in Neural Information Processing Systems 33, 10328-10337, 2020
862020
Beating stochastic and adversarial semi-bandits optimally and simultaneously
J Zimmert, H Luo, CY Wei
International Conference on Machine Learning, 7683-7692, 2019
812019
An optimal algorithm for adversarial bandits with arbitrary delays
J Zimmert, Y Seldin
International Conference on Artificial Intelligence and Statistics, 3285-3294, 2020
502020
Connections between mirror descent, Thompson sampling and the information ratio
J Zimmert, T Lattimore
Advances in Neural Information Processing Systems 32, 2019
392019
A model selection approach for corruption robust reinforcement learning
CY Wei, C Dann, J Zimmert
International Conference on Algorithmic Learning Theory, 1043-1096, 2022
382022
A provably efficient model-free posterior sampling method for episodic reinforcement learning
C Dann, M Mohri, T Zhang, J Zimmert
Advances in Neural Information Processing Systems 34, 12040-12051, 2021
302021
Beyond value-function gaps: Improved instance-dependent regret bounds for episodic reinforcement learning
C Dann, TV Marinov, M Mohri, J Zimmert
Advances in Neural Information Processing Systems 34, 1-12, 2021
282021
Safe screening for support vector machines
J Zimmert, CS de Witt, G Kerg, M Kloft
NIPS 2015 Workshop on Optimization in Machine Learning (OPT), 2015
222015
The pareto frontier of model selection for general contextual bandits
TV Marinov, J Zimmert
Advances in Neural Information Processing Systems 34, 17956-17967, 2021
182021
Pushing the efficiency-regret Pareto frontier for online learning of portfolios and quantum states
J Zimmert, N Agarwal, S Kale
Conference on Learning Theory, 182-226, 2022
172022
A blackbox approach to best of both worlds in bandits and beyond
C Dann, CY Wei, J Zimmert
The Thirty Sixth Annual Conference on Learning Theory, 5503-5570, 2023
162023
Factored bandits
J Zimmert, Y Seldin
Advances in Neural Information Processing Systems 31, 2018
162018
Distributed optimization of multi-class SVMs
M Alber, J Zimmert, U Dogan, M Kloft
PloS one 12 (6), e0178161, 2017
142017
Refined regret for adversarial mdps with linear function approximation
Y Dai, H Luo, CY Wei, J Zimmert
International Conference on Machine Learning, 6726-6759, 2023
132023
A best-of-both-worlds algorithm for bandits with delayed feedback
S Masoudian, J Zimmert, Y Seldin
Advances in Neural Information Processing Systems 35, 11752-11762, 2022
132022
Return of the bias: Almost minimax optimal high probability bounds for adversarial linear bandits
J Zimmert, T Lattimore
Conference on Learning Theory, 3285-3312, 2022
102022
Best of both worlds policy optimization
C Dann, CY Wei, J Zimmert
International Conference on Machine Learning, 6968-7008, 2023
82023
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20