Follow
Sanae Amani
Sanae Amani
Verified email at ucla.edu - Homepage
Title
Cited by
Cited by
Year
Linear stochastic bandits under safety constraints
S Amani, M Alizadeh, C Thrampoulidis
Advances in Neural Information Processing Systems 32, 2019
522019
Safe linear thompson sampling with side information
A Moradipari, S Amani, M Alizadeh, C Thrampoulidis
IEEE Transactions on Signal Processing 69, 3755-3767, 2021
19*2021
Regret bound for safe gaussian process bandit optimization
S Amani, M Alizadeh, C Thrampoulidis
Learning for Dynamics and Control, 158-159, 2020
132020
Generalized linear bandits with safety constraints
S Amani, M Alizadeh, C Thrampoulidis
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
72020
Safe Reinforcement Learning with Linear Function Approximation
S Amani, C Thrampoulidis, LF Yang
International Conference on Machine Learning, 243-253, 2021
62021
Decentralized Multi-Agent Linear Bandits with Safety Constraints
S Amani, C Thrampoulidis
Proceedings of the AAAI Conference on Artificial Intelligence 35 (8), 6627-6635, 2021
32021
UCB-based Algorithms for Multinomial Logistic Regression Bandits
S Amani, C Thrampoulidis
Advances in Neural Information Processing Systems 34, 2913-2924, 2021
12021
Provably Efficient Lifelong Reinforcement Learning with Linear Function Approximation
S Amani, LF Yang, CA Cheng
arXiv preprint arXiv:2206.00270, 2022
2022
Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost
S Amani, T Lattimore, A György, LF Yang
arXiv preprint arXiv:2205.13170, 2022
2022
Doubly Pessimistic Algorithms for Strictly Safe Off-Policy Optimization
S Amani, LF Yang
2022 56th Annual Conference on Information Sciences and Systems (CISS), 113-118, 2022
2022
A generalization of weighted sparse decomposition to negative weights
G Delfi, S Aziznejad, S Amani, M Babaie-Zadeh, C Jutten
2017 25th European Signal Processing Conference (EUSIPCO), 2146-2150, 2017
2017
The system can't perform the operation now. Try again later.
Articles 1–11