5 papers
Wasserstein Stability and Free Boundaries in Measure-Parameterized Bilevel Obstacle Problems
Kun Huang
We study obstacle-constrained variational problems whose reduced energies depend on a probability law through a lower-level optimizer. Uniform strong convexity yields a single-valu…
Distributed Random Reshuffling Methods with Improved Convergence
Kun Huang, Linli Zhou, Shi Pu
This paper proposes two distributed random reshuffling methods, namely Gradient Tracking with Random Reshuffling (GT-RR) and Exact Diffusion with Random Reshuffling (ED-RR), to sol…
Distributed Random Reshuffling over Networks
Kun Huang, Xiao Li, Andre Milzarek +2
In this paper, we consider distributed optimization problems where agents, each possessing a local cost function, collaboratively minimize the average of the local cost functio…
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…
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…