no code implementations • 31 Jan 2024 • Xuefeng Gao, Lingjiong Zhu
Score-based generative modeling with probability flow ordinary differential equations (ODEs) has achieved remarkable success in a variety of applications.
no code implementations • 18 Nov 2023 • Xuefeng Gao, Hoang M. Nguyen, Lingjiong Zhu
We find that the experimental results are in good agreement with our theoretical predictions on the iteration complexity, and the models with our newly proposed forward processes can outperform existing models.
no code implementations • 30 Jan 2023 • Wenhao Xu, Xuefeng Gao, Xuedong He
The optimized certainty equivalent (OCE) is a family of risk measures that cover important examples such as entropic risk, conditional value-at-risk and mean-variance models.
no code implementations • 3 Oct 2022 • Xuefeng Gao, Xun Yu Zhou
We study reinforcement learning for continuous-time Markov decision processes (MDPs) in the finite-horizon episodic setting.
no code implementations • 23 May 2022 • Xuefeng Gao, Xun Yu Zhou
We consider reinforcement learning for continuous-time Markov decision processes (MDPs) in the infinite-horizon, average-reward setting.
no code implementations • 31 Jul 2021 • Ningyuan Chen, Xuefeng Gao, Yi Xiong
It has been recently shown in the literature that the sample averages from online learning experiments are biased when used to estimate the mean reward.
no code implementations • 8 Jul 2021 • Yi Xiong, Ningyuan Chen, Xuefeng Gao, Xiang Zhou
We study the model-based undiscounted reinforcement learning for partially observable Markov decision processes (POMDPs).
no code implementations • NeurIPS 2020 • Xuefeng Gao, Mert Gurbuzbalaban, Lingjiong Zhu
We study two variants that are based on non-reversible Langevin diffusions: the underdamped Langevin dynamics (ULD) and the Langevin dynamics with a non-symmetric drift (NLD).
no code implementations • 15 Nov 2020 • Xuefeng Gao, Zuo Quan Xu, Xun Yu Zhou
We study the temperature control problem for Langevin diffusions in the context of non-convex optimization.
no code implementations • 1 Jul 2020 • Mert Gürbüzbalaban, Xuefeng Gao, Yuanhan Hu, Lingjiong Zhu
Stochastic gradient Langevin dynamics (SGLD) and stochastic gradient Hamiltonian Monte Carlo (SGHMC) are two popular Markov Chain Monte Carlo (MCMC) algorithms for Bayesian inference that can scale to large datasets, allowing to sample from the posterior distribution of the parameters of a statistical model given the input data and the prior distribution over the model parameters.
no code implementations • LREC 2020 • Rong Xiang, Xuefeng Gao, Yunfei Long, Anran Li, Emmanuele Chersoni, Qin Lu, Chu-Ren Huang
Automatic Chinese irony detection is a challenging task, and it has a strong impact on linguistic research.
no code implementations • 6 Apr 2020 • Yuanhan Hu, Xiaoyu Wang, Xuefeng Gao, Mert Gurbuzbalaban, Lingjiong Zhu
In this paper, we study the non reversible Stochastic Gradient Langevin Dynamics (NSGLD) which is based on discretization of the non-reversible Langevin diffusion.
no code implementations • NeurIPS 2021 • Xiang Zhou, Yi Xiong, Ningyuan Chen, Xuefeng Gao
We study a multi-armed bandit problem where the rewards exhibit regime switching.
no code implementations • 19 Dec 2018 • Xuefeng Gao, Mert Gurbuzbalaban, Lingjiong Zhu
We study two variants that are based on non-reversible Langevin diffusions: the underdamped Langevin dynamics (ULD) and the Langevin dynamics with a non-symmetric drift (NLD).
no code implementations • 12 Sep 2018 • Xuefeng Gao, Mert Gürbüzbalaban, Lingjiong Zhu
We provide finite-time performance bounds for the global convergence of both SGHMC variants for solving stochastic non-convex optimization problems with explicit constants.
no code implementations • 15 Jun 2018 • Xuefeng Gao, Yunhan Wang
This paper studies optimal market making for large-tick assets in the presence of latency.