6 papers · 1 filter
A Single-loop Stochastic Riemannian ADMM for Nonsmooth Optimization
Jiachen Jin, Kangkang Deng, Hongxia Wang
We study a class of nonsmooth stochastic optimization problems on Riemannian manifolds. In this work, we propose MARS-ADMM, the first stochastic Riemannian alternating direction me…
Adaptive Riemannian ADMM for Nonsmooth Optimization: Optimal Complexity without Smoothing
Kangkang Deng, Jiachen Jin, Jiang Hu +1
We study the problem of minimizing the sum of a smooth function and a nonsmooth convex regularizer over a compact Riemannian submanifold embedded in Euclidean space. By introducing…
Single-loop stochastic smoothing algorithms for nonsmooth Riemannian optimization
Kangkang Deng, Zheng Peng, Weihe Wu
In this paper, we develop two Riemannian stochastic smoothing algorithms for nonsmooth optimization problems on Riemannian manifolds, addressing distinct forms of the nonsmooth ter…
Stochastic ADMM with batch size adaptation for nonconvex nonsmooth optimization
Jiachen Jin, Kangkang Deng, Boyu Wang +1
Stochastic alternating direction method of multipliers (SADMM) is a popular method for solving nonconvex nonsmooth optimization in various applications. However, it typically requi…
Stochastic momentum ADMM for nonconvex and nonsmooth optimization with application to PnP algorithm
Kangkang Deng, Shuchang Zhang, Boyu Wang +3
This paper proposes SMADMM, a single-loop Stochastic Momentum Alternating Direction Method of Multipliers for solving a class of nonconvex and nonsmooth composite optimization prob…
Inexact Riemannian Gradient Descent Method for Nonconvex Optimization
Juan Zhou, Kangkang Deng, Hongxia Wang +1
Gradient descent methods are fundamental first-order optimization algorithms in both Euclidean spaces and Riemannian manifolds. However, the exact gradient is not readily available…