no code implementations • 4 Dec 2023 • Tiancheng Qin, S. Rasoul Etesami
Specifically, under no assumptions on the reward functions, we show the proposed algorithm converges in polynomial time in a weaker distance (namely, the averaged Nikaido-Isoda gap) to the set of $\epsilon$-NE policies with arbitrarily high probability.
no code implementations • 3 Nov 2022 • Masood S. Mortazavi, Tiancheng Qin, Ning Yan
Given an environment (e. g., a simulator) for evaluating samples in a specified design space and a set of weighted evaluation metrics -- one can use Theta-Resonance, a single-step Markov Decision Process (MDP), to train an intelligent agent producing progressively more optimal samples.
no code implementations • 14 Mar 2022 • Tiancheng Qin, S. Rasoul Etesami, César A. Uribe
Our main contribution is to characterize the convergence rate of Local SGD as a function of $\{H_i\}_{i=1}^R$ under various settings of strongly convex, convex, and nonconvex local functions, where $R$ is the total number of communication rounds.
no code implementations • 30 Jan 2022 • Tiancheng Qin, S. Rasoul Etesami, César A. Uribe
For general convex loss functions, we establish an error bound of $\O(1/T)$ under a mild data similarity assumption and an error bound of $\O(K/T)$ otherwise, where $K$ is the number of local steps.
no code implementations • 6 Nov 2020 • Tiancheng Qin, S. Rasoul Etesami, César A. Uribe
Agents have access to $F$ through noisy gradients, and they can locally communicate with their neighbors a network.