48 citations · 54 across the 5 of their papers we have counts for
5 papers
A Graph Regularized Point Process Model For Event Propagation Sequence
Siqiao Xue, Xiaoming Shi, Hongyan Hao +4
Point process is the dominant paradigm for modeling event sequences occurring at irregular intervals. In this paper we aim at modeling latent dynamics of event propagation in graph…
A Meta Reinforcement Learning Approach for Predictive Autoscaling in the Cloud
Siqiao Xue, Chao Qu, Xiaoming Shi +11
Predictive autoscaling (autoscaling with workload forecasting) is an important mechanism that supports autonomous adjustment of computing resources in accordance with fluctuating w…
Neural Physicist: Learning Physical Dynamics from Image Sequences
Baocheng Zhu, Shijun Wang, James Zhang
We present a novel architecture named Neural Physicist (NeurPhy) to learn physical dynamics directly from image sequences using deep neural networks. For any physical system, given…
Riemannian Proximal Policy Optimization
Shijun Wang, Baocheng Zhu, Chen Li +4
In this paper, We propose a general Riemannian proximal optimization algorithm with guaranteed convergence to solve Markov decision process (MDP) problems. To model policy function…
A Riemannian Primal-dual Algorithm Based on Proximal Operator and its Application in Metric Learning
Shijun Wang, Baocheng Zhu, Lintao Ma +1
In this paper, we consider optimizing a smooth, convex, lower semicontinuous function in Riemannian space with constraints. To solve the problem, we first convert it to a dual prob…