Showing math.OCShow all
2 papers · 1 filter
math.OC2020
Distributed Gradient Flow: Nonsmoothness, Nonconvexity, and Saddle Point Evasion
Brian Swenson, Ryan Murray, H. Vincent Poor +1
The paper considers distributed gradient flow (DGF) for multi-agent nonconvex optimization. DGF is a continuous-time approximation of distributed gradient descent that is often eas…
math.OC2019
Distributed Gradient Descent: Nonconvergence to Saddle Points and the Stable-Manifold Theorem
Brian Swenson, Ryan Murray, H. Vincent Poor +1
The paper studies a distributed gradient descent (DGD) process and considers the problem of showing that in nonconvex optimization problems, DGD typically converges to local minima…