2 papers
math.OC2021
Compressed Gradient Tracking Methods for Decentralized Optimization with Linear Convergence
Yiwei Liao, Zhuorui Li, Kun Huang +1
Communication compression techniques are of growing interests for solving the decentralized optimization problem under limited communication, where the global objective is to minim…
cond-mat.dis-nn2017
Connecting phase transition theory with unsupervised learning
Kun Huang
Entropy and order parameter are two key concepts in phase transition theory. This paper proposes an unified method to both find order parameter and estimate entropy automatically w…