A Riemannian ADMM

11/03/2022
by   Jiaxiang Li, et al.
5

We consider a class of Riemannian optimization problems where the objective is the sum of a smooth function and a nonsmooth function, considered in the ambient space. This class of problems finds important applications in machine learning and statistics such as the sparse principal component analysis, sparse spectral clustering, and orthogonal dictionary learning. We propose a Riemannian alternating direction method of multipliers (ADMM) to solve this class of problems. Our algorithm adopts easily computable steps in each iteration. The iteration complexity of the proposed algorithm for obtaining an ϵ-stationary point is analyzed under mild assumptions. To the best of our knowledge, this is the first Riemannian ADMM with provable convergence guarantee for solving Riemannian optimization problem with nonsmooth objective. Numerical experiments are conducted to demonstrate the advantage of the proposed method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/08/2020

Alternating Direction Method of Multipliers for Quantization

Quantization of the parameters of machine learning models, such as deep ...
research
11/12/2019

Nonsmooth Optimization over Stiefel Manifold: Riemannian Subgradient Methods

Nonsmooth Riemannian optimization is a still under explored subfield of ...
research
12/15/2021

On Generalization and Computation of Tukey's Depth: Part II

This paper studies how to generalize Tukey's depth to problems defined i...
research
10/05/2017

Primal-Dual Optimization Algorithms over Riemannian Manifolds: an Iteration Complexity Analysis

In this paper we study nonconvex and nonsmooth multi-block optimization ...
research
10/18/2017

A Memristor-Based Optimization Framework for AI Applications

Memristors have recently received significant attention as ubiquitous de...
research
06/21/2017

Scalable Online Convolutional Sparse Coding

Convolutional sparse coding (CSC) improves sparse coding by learning a s...
research
12/08/2017

Nonconvex Sparse Spectral Clustering by Alternating Direction Method of Multipliers and Its Convergence Analysis

Spectral Clustering (SC) is a widely used data clustering method which f...

Please sign up or login with your details

Forgot password? Click here to reset