Следене
Sattar Vakili
Sattar Vakili
MediaTek Research
Потвърден имейл адрес: mtkresearch.com
Заглавие
Позовавания
Позовавания
Година
Deterministic sequencing of exploration and exploitation for multi-armed bandit problems
S Vakili, K Liu, Q Zhao
IEEE Journal of Selected Topics in Signal Processing 7 (5), 759-767, 2013
1112013
Risk-averse multi-armed bandit problems under mean-variance measure
S Vakili, Q Zhao
IEEE Journal of Selected Topics in Signal Processing 10 (6), 1093-1111, 2016
792016
On information gain and regret bounds in gaussian process bandits
S Vakili, K Khezeli, V Picheny
International Conference on Artificial Intelligence and Statistics, 82-90, 2021
492021
Mean-variance and value at risk in multi-armed bandit problems
S Vakili, Q Zhao
2015 53rd Annual Allerton Conference on Communication, Control, and …, 2015
322015
Adaptive sensor placement for continuous spaces
JA Grant, A Boukouvalas, RR Griffiths, DS Leslie, S Vakili, EM De Cote
http://proceedings.mlr.press/v97/grant19a.html 97, 2385-2393, 2019
172019
Scalable Thompson Sampling using Sparse Gaussian Process Models
S Vakili, H Moss, A Artemev, V Dutordoir, V Picheny
Advances in Neural Information Processing Systems 34, 2021
162021
Optimal order simple regret for Gaussian process bandits
S Vakili, N Bouziani, S Jalali, A Bernacchia, D Shiu
Advances in Neural Information Processing Systems 34, 21202-21215, 2021
132021
A domain-shrinking based Bayesian optimization algorithm with order-optimal regret performance
S Salgia, S Vakili, Q Zhao
Advances in Neural Information Processing Systems 34, 28836-28847, 2021
12*2021
Regret Bounds for Noise-Free Kernel-Based Bandits
S Vakili
Conference on Learning Theory, 2022, 2020
10*2020
A random walk approach to first-order stochastic convex optimization
S Vakili, Q Zhao
2019 IEEE International Symposium on Information Theory (ISIT), 395-399, 2019
102019
Hierarchical heavy hitter detection under unknown models
S Vakili, Q Zhao, C Liu, CN Chuah
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
102018
Achieving complete learning in multi-armed bandit problems
S Vakili, Q Zhao
2013 Asilomar Conference on Signals, Systems and Computers, 1778-1782, 2013
102013
Open problem: Tight online confidence intervals for rkhs elements
S Vakili, J Scarlett, T Javidi
Conference on Learning Theory, 4647-4652, 2021
82021
Decision variance in risk-averse online learning
S Vakili, A Boukouvalas, Q Zhao
2019 IEEE 58th Conference on Decision and Control (CDC), 2738-2744, 2019
8*2019
Risk-averse online learning under mean-variance measures
S Vakili, Q Zhao
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
82015
Stochastic Gradient Descent on a Tree: An Adaptive and Robust Approach to Stochastic Convex Optimization
S Vakili, S Salgia, Q Zhao
2019 57th Annual Allerton Conference on Communication, Control, and …, 2019
62019
Time-varying stochastic multi-armed bandit problems
S Vakili, Q Zhao, Y Zhou
2014 48th Asilomar Conference on Signals, Systems and Computers, 2103-2107, 2014
62014
Uniform generalization bounds for overparameterized neural networks
S Vakili, M Bromberg, J Garcia, D Shiu, A Bernacchia
arXiv preprint arXiv:2109.06099, 2021
52021
Online learning with side information
X Xu, S Vakili, Q Zhao, A Swami
MILCOM 2017-2017 IEEE military communications conference (MILCOM), 303-308, 2017
52017
Multi-armed bandits on partially revealed unit interval graphs
X Xu, S Vakili, Q Zhao, A Swami
IEEE Transactions on Network Science and Engineering 7 (3), 1453-1465, 2019
42019
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–20