Prati
Chicheng Zhang
Chicheng Zhang
Potvrđena adresa e-pošte na cs.arizona.edu - Početna stranica
Naslov
Citirano
Citirano
Godina
Deep batch active learning by diverse, uncertain gradient lower bounds
JT Ash, C Zhang, A Krishnamurthy, J Langford, A Agarwal
arXiv preprint arXiv:1906.03671, 2019
6792019
Active learning from weak and strong labelers
C Zhang, K Chaudhuri
Advances in Neural Information Processing Systems 28, 2015
1032015
Beyond disagreement-based agnostic active learning
C Zhang, K Chaudhuri
Advances in Neural Information Processing Systems 27, 2014
972014
Contextual bandits with continuous actions: Smoothing, zooming, and adapting
A Krishnamurthy, J Langford, A Slivkins, C Zhang
Journal of Machine Learning Research 21 (137), 1-45, 2020
682020
Revisiting perceptron: Efficient and label-optimal learning of halfspaces
S Yan, C Zhang
Advances in Neural Information Processing Systems 30, 2017
542017
Efficient active learning of sparse halfspaces
C Zhang
Conference on Learning Theory, 1856-1880, 2018
382018
Efficient active learning of sparse halfspaces with arbitrary bounded noise
C Zhang, J Shen, P Awasthi
Advances in Neural Information Processing Systems 33, 7184-7197, 2020
332020
Search improves label for active learning
A Beygelzimer, DJ Hsu, J Langford, C Zhang
Advances in neural information processing systems 29, 2016
312016
Efficient contextual bandits with continuous actions
M Majzoubi, C Zhang, R Chari, A Krishnamurthy, J Langford, A Slivkins
Advances in Neural Information Processing Systems 33, 349-360, 2020
302020
Warm-starting contextual bandits: Robustly combining supervised and bandit feedback
C Zhang, A Agarwal, H Daumé III, J Langford, SN Negahban
arXiv preprint arXiv:1901.00301, 2019
282019
The extended littlestone’s dimension for learning with mistakes and abstentions
C Zhang, K Chaudhuri
Conference on learning theory, 1584-1616, 2016
252016
Multitask bandit learning through heterogeneous feedback aggregation
Z Wang, C Zhang, MK Singh, L Riek, K Chaudhuri
International Conference on Artificial Intelligence and Statistics, 1531-1539, 2021
22*2021
Efficient Online Bandit Multiclass Learning with Regret
A Beygelzimer, F Orabona, C Zhang
International Conference on Machine Learning, 488-497, 2017
222017
Improved algorithms for efficient active learning halfspaces with massart and tsybakov noise
C Zhang, Y Li
Conference on Learning Theory, 4526-4527, 2021
212021
Active online learning with hidden shifting domains
Y Chen, H Luo, T Ma, C Zhang
International Conference on Artificial Intelligence and Statistics, 2053-2061, 2021
18*2021
Provably efficient multi-task reinforcement learning with model transfer
C Zhang, Z Wang
Advances in Neural Information Processing Systems 34, 19771-19783, 2021
172021
Active fairness auditing
T Yan, C Zhang
International Conference on Machine Learning, 24929-24962, 2022
162022
Crush optimism with pessimism: Structured bandits beyond asymptotic optimality
KS Jun, C Zhang
Advances in Neural Information Processing Systems 33, 6366-6376, 2020
152020
Bandit multiclass linear classification: Efficient algorithms for the separable case
A Beygelzimer, D Pal, B Szorenyi, D Thiruvenkatachari, CY Wei, C Zhang
International Conference on Machine Learning, 624-633, 2019
142019
Attribute-efficient learning of halfspaces with malicious noise: Near-optimal label complexity and noise tolerance
J Shen, C Zhang
Algorithmic Learning Theory, 1072-1113, 2021
112021
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20