11 citations · 26 across the 12 of their papers we have counts for
12 papers
Residual-Quantile Adjustment for Adaptive Training of Physics-informed Neural Network
Jiayue Han, Zhiqiang Cai, Zhiyou Wu +1
Adaptive training methods for Physics-informed neural network (PINN) require dedicated constructions of the distribution of weights assigned at each training sample. To efficiently…
Learn Quasi-stationary Distributions of Finite State Markov Chain
Zhiqiang Cai, Ling Lin, Xiang Zhou
We propose a reinforcement learning (RL) approach to compute the expression of quasi-stationary distribution. Based on the fixed-point formulation of quasi-stationary distribution,…
Sublinear Regret for Learning POMDPs
Yi Xiong, Ningyuan Chen, Xuefeng Gao +1
We study the model-based undiscounted reinforcement learning for partially observable Markov decision processes (POMDPs). The oracle we consider is the optimal policy of the POMDP…
Roughness Index for Loss Landscapes of Neural Network Models of Partial Differential Equations
Keke Wu, Xiangru Jian, Rui Du +2
Loss landscape is a useful tool to characterize and compare neural network models. The main challenge for analysis of loss landscape for the deep neural networks is that they are g…
Value-Gradient based Formulation of Optimal Control Problem and Machine Learning Algorithm
Alain Bensoussan, Jiayue Han, Sheung Chi Phillip Yam +1
Optimal control problem is typically solved by first finding the value function through Hamilton-Jacobi equation (HJE) and then taking the minimizer of the Hamiltonian to obtain th…
Projection Method for Saddle Points of Energy Functional in Metric
Shuting Gu, Ling Lin, Xiang Zhou
Saddle points play important roles as the transition states of activated process in gradient system driven by energy functional. However, for the same energy functional, the saddle…
Machine Learning and Control Theory
Alain Bensoussan, Yiqun Li, Dinh Phan Cao Nguyen +3
We survey in this article the connections between Machine Learning and Control Theory. Control Theory provide useful concepts and tools for Machine Learning. Conversely Machine Lea…
Enumerating Chemical Graphs with Two Disjoint Cycles Satisfying Given Path Frequency Specifications
Kyousuke Yamashita, Ryuji Masui, Xiang Zhou +4
Enumerating chemical graphs satisfying given constraints is a fundamental problem in mathematical and computational chemistry, and plays an essential part in a recently proposed fr…
Explicit Estimation of Derivatives from Data and Differential Equations by Gaussian Process Regression
Hongqiao Wang, Xiang Zhou
In this work, we employ the Bayesian inference framework to solve the problem of estimating the solution and particularly, its derivatives, which satisfy a known differential equat…
Stochastic Modified Equations for Continuous Limit of Stochastic ADMM
Xiang Zhou, Huizhuo Yuan, Chris Junchi Li +1
Stochastic version of alternating direction method of multiplier (ADMM) and its variants (linearized ADMM, gradient-based ADMM) plays a key role for modern large scale machine lear…
Regime Switching Bandits
Xiang Zhou, Yi Xiong, Ningyuan Chen +1
We study a multi-armed bandit problem where the rewards exhibit regime switching. Specifically, the distributions of the random rewards generated from all arms are modulated by a c…
Fine-grained Attention and Feature-sharing Generative Adversarial Networks for Single Image Super-Resolution
Yitong Yan, Chuangchuang Liu, Changyou Chen +3
The traditional super-resolution methods that aim to minimize the mean square error usually produce the images with over-smoothed and blurry edges, due to the lose of high-frequenc…