no code implementations • 31 Mar 2022 • Shaocong Ma, Ziyi Chen, Yi Zhou, Kaiyi Ji, Yingbin Liang
Moreover, we show that online SGD with mini-batch sampling can further substantially improve the sample complexity over online SGD with periodic data-subsampling over highly dependent data.
no code implementations • 22 Dec 2021 • Ziyi Chen, Shaocong Ma, Yi Zhou
Alternating gradient-descent-ascent (AltGDA) is an optimization algorithm that has been widely used for model training in various machine learning applications, which aims to solve a nonconvex minimax optimization problem.
no code implementations • ICLR 2022 • Ziyi Chen, Shaocong Ma, Yi Zhou
Two-player zero-sum Markov game is a fundamental problem in reinforcement learning and game theory.
no code implementations • 29 Sep 2021 • Shaocong Ma, Ziyi Chen, Yi Zhou, Kaiyi Ji, Yingbin Liang
Specifically, with a $\phi$-mixing model that captures both exponential and polynomial decay of the data dependence over time, we show that SGD with periodic data-subsampling achieves an improved sample complexity over the standard SGD in the full spectrum of the $\phi$-mixing data dependence.
no code implementations • ICLR 2021 • Shaocong Ma, Ziyi Chen, Yi Zhou, Shaofeng Zou
Greedy-GQ is a value-based reinforcement learning (RL) algorithm for optimal control.
no code implementations • NeurIPS 2020 • Shaocong Ma, Yi Zhou, Shaofeng Zou
In the Markovian setting, our algorithm achieves the state-of-the-art sample complexity $O(\epsilon^{-1} \log {\epsilon}^{-1})$ that is near-optimal.
no code implementations • ICML 2020 • Shaocong Ma, Yi Zhou
Specifically, minimizer incoherence measures the discrepancy between the global minimizers of a sample loss and those of the total loss and affects the convergence error of SGD with random reshuffle.