most citedDecentralized Riemannian natural gradient methods with Kronecker-product approximations

1 citations · 1 across the 5 of their papers we have counts for

collaborators

5 papers

math.OC2024

Improving the communication in decentralized manifold optimization through single-step consensus and compression

Jiang Hu, Kangkang Deng

We are concerned with decentralized optimization over a compact submanifold, where the loss functions of local datasets are defined by their respective local datasets. A key challe…

math.OC2024

Oracle complexities of augmented Lagrangian methods for nonsmooth manifold optimization

Kangkang Deng, Jiang Hu, Jiayuan Wu +1

In this paper, we present two novel manifold inexact augmented Lagrangian methods, \textbf{ManIAL} for deterministic settings and \textbf{StoManIAL} for stochastic settings, solvin…

math.OC2023

Achieving Consensus over Compact Submanifolds

Jiang Hu, Jiaojiao Zhang, Kangkang Deng

We consider the consensus problem in a decentralized network, focusing on a compact submanifold that acts as a nonconvex constraint set. By leveraging the proximal smoothness of th…

math.OC20231 cited

Decentralized Riemannian natural gradient methods with Kronecker-product approximations

Jiang Hu, Kangkang Deng, Na Li +1

With a computationally efficient approximation of the second-order information, natural gradient methods have been successful in solving large-scale structured optimization problem…

math.OC2023

A projected semismooth Newton method for a class of nonconvex composite programs with strong prox-regularity

Jiang Hu, Kangkang Deng, Jiayuan Wu +1

This paper aims to develop a Newton-type method to solve a class of nonconvex composite programs. In particular, the nonsmooth part is possibly nonconvex. To tackle the nonconvexit…