7 papers · 1 filter
An Inexact Riemannian Proximal Momentum Variance-Reduced Method: Complexity Bounds and KL Sequential Convergence
Na Zhang
We develop a unified analysis of inexact stochastic Riemannian proximal optimization for finite-sum nonsmooth composite problems over compact embedded submanifolds. The framework a…
An efficient proximal algorithm for squared L1 over L2 regularized sparse recovery
Na Zhang, Hong Chen, Qia Li +1
In this paper, we consider a squared regularized model for sparse signal recovery from noisy measurements. We first establish the existence of optimal solutions to the mo…
A min-max reformulation and proximal algorithms for a class of structured nonsmooth fractional optimization problems
Junpeng Zhou, Na Zhang, Qia Li
In this paper, we consider a class of structured nonsmooth fractional minimization, where the first part of the objective is the ratio of a nonnegative nonsmooth nonconvex function…
Proximal methods for structured nonsmooth optimization over Riemannian submanifolds
Qia Li, Na Zhang, Junyu Feng +1
In this paper, we consider a class of structured nonsmooth optimization problems over an embedded submanifold of a Euclidean space, where the first part of the objective is the sum…
An equivalent reformulation and multi-proximity gradient algorithms for a class of nonsmooth fractional programming
Junpeng Zhou, Na Zhang, Qia Li
In this paper, we consider a class of structured fractional programs, where the numerator part is the sum of a block-separable (possibly nonsmooth nonconvex) function and a locally…
A Successive Two-stage Method for Sparse Generalized Eigenvalue Problems
Qia Li, Jianmin Liao, Lixin Shen +1
The Sparse Generalized Eigenvalue Problem (sGEP), a pervasive challenge in statistical learning methods including sparse principal component analysis, sparse Fisher's discriminant…