Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Pham, Nhan H."'
In recent years, a proliferation of methods were developed for cooperative multi-agent reinforcement learning (c-MARL). However, the robustness of c-MARL agents against adversarial attacks has been rarely explored. In this paper, we propose to evalua
Externí odkaz:
http://arxiv.org/abs/2202.03558
Publikováno v:
NeurIPs 2021
We develop two new algorithms, called, FedDR and asyncFedDR, for solving a fundamental nonconvex composite optimization problem in federated learning. Our algorithms rely on a novel combination between a nonconvex Douglas-Rachford splitting method, r
Externí odkaz:
http://arxiv.org/abs/2103.03452
Motivated by broad applications in reinforcement learning and machine learning, this paper considers the popular stochastic gradient descent (SGD) when the gradients of the underlying objective function are sampled from Markov processes. This Markov
Externí odkaz:
http://arxiv.org/abs/2003.10973
Autor:
Pham, Nhan H., Nguyen, Lam M., Phan, Dzung T., Nguyen, Phuong Ha, van Dijk, Marten, Tran-Dinh, Quoc
Publikováno v:
Proceedings of the International Conference on Artificial Intelligence and Statistics, PMLR 108:374-385, 2020
We propose a novel hybrid stochastic policy gradient estimator by combining an unbiased policy gradient estimator, the REINFORCE estimator, with another biased one, an adapted SARAH estimator for policy optimization. The hybrid policy gradient estima
Externí odkaz:
http://arxiv.org/abs/2003.00430
Publikováno v:
ICML 2020
We develop two new stochastic Gauss-Newton algorithms for solving a class of non-convex stochastic compositional optimization problems frequently arising in practice. We consider both the expectation and finite-sum settings under standard assumptions
Externí odkaz:
http://arxiv.org/abs/2002.07290
Convergence Rates of Accelerated Markov Gradient Descent with Applications in Reinforcement Learning
Motivated by broad applications in machine learning, we study the popular accelerated stochastic gradient descent (ASGD) algorithm for solving (possibly nonconvex) optimization problems. We characterize the finite-time performance of this method when
Externí odkaz:
http://arxiv.org/abs/2002.02873
We introduce a new approach to develop stochastic optimization algorithms for a class of stochastic composite and possibly nonconvex optimization problems. The main idea is to combine two stochastic estimators to create a new hybrid one. We first int
Externí odkaz:
http://arxiv.org/abs/1907.03793
We introduce a hybrid stochastic estimator to design stochastic gradient algorithms for solving stochastic optimization problems. Such a hybrid estimator is a convex combination of two existing biased and unbiased estimators and leads to some useful
Externí odkaz:
http://arxiv.org/abs/1905.05920
We propose a new stochastic first-order algorithmic framework to solve stochastic composite nonconvex optimization problems that covers both finite-sum and expectation settings. Our algorithms rely on the SARAH estimator introduced in (Nguyen et al,
Externí odkaz:
http://arxiv.org/abs/1902.05679
Autor:
Tran-Dinh, Quoc1 (AUTHOR) quoctd@email.unc.edu, Pham, Nhan H.1 (AUTHOR), Phan, Dzung T.2 (AUTHOR), Nguyen, Lam M.2 (AUTHOR)
Publikováno v:
Mathematical Programming. Feb2022, Vol. 191 Issue 2, p1005-1071. 67p.
