4 papers
Convergence Analysis of Noisy Distributed Gradient Descent for Non-convex Optimization -- Saddle Point Escape
Lei Qin, Michael Cantoni, Ye Pu
A variant of consensus based distributed gradient descent (\textbf{DGD}) is studied for finite sums of smooth but possibly non-convex functions. In particular, the local gradient t…
Two-timescale EXTRA for Distributed Smooth Non-convex Optimization
Zeyu Peng, Farhad Farokhi, Ye Pu
In this paper, we study distributed optimization with smooth non-convex local objectives. We propose a novel variant of the well-known EXact firsT-ordeR Algorithm (EXTRA), called T…
On the Convergence of a Noisy Gradient Method for Non-convex Distributed Resource Allocation: Saddle Point Escape
Lei Qin, Ye Pu
This paper considers a class of distributed resource allocation problems where each agent privately holds a smooth, potentially non-convex local objective, subject to a globally co…
Convergence Analysis of EXTRA in Non-convex Distributed Optimization
Lei Qin, Ye Pu
Optimization problems involving the minimization of a finite sum of smooth, possibly non-convex functions arise in numerous applications. To achieve a consensus solution over a net…