Bicheng Ying

TL;DR: The exact diffusion method is applicable to locally balanced left-stochastic combination matrices which, compared to the conventional doubly stochastic matrix, are more general and able to endow the algorithm with faster convergence rates, more flexible step-size choices, and improved privacy-preserving properties.

TL;DR: In this paper, a distributed optimization strategy with guaranteed exact convergence for a broad class of left-stochastic combination policies was developed, which is applicable to locally balanced combination matrices which are more general and able to endow the algorithm with faster convergence rates, more flexible step-size choices, and improved privacy-preserving properties.

TL;DR: In this paper, the exact diffusion algorithm was developed to remove the bias that is characteristic of distributed solutions for deterministic optimization problems, and the algorithm was shown to be applicable to a larger set of locally balanced left-stochastic combination policies than the set of doubly-state stochastic policies.

TL;DR: In this paper, a distributed variance-reduced strategy for a collection of interacting agents that are connected by a graph topology is developed, which is shown to have linear convergence to the exact solution, and is more memory efficient than other alternative algorithms.

TL;DR: It is shown that the asymmetric flow of information hinders the learning abilities of certain agents regardless of their local observations, and useful closed-form expressions are derived which can be used to motivate design problems to control it.