Work

Large-scale randomized-coordinate descent methods with non-separable linear constraints

Year: 2014

Type: preprint

Abstract: We develop randomized (block) coordinate descent (CD) methods for linearly constrained convex optimization. Unlike most CD methods, we do not assume the constraints to be separable, but let them be coupled linearly. To our knowledge, ours is the first CD method that allows linear coupling constraints, without making the global iteration complexity have an exponential dependence on the number of constraints. We present algorithms and analysis for four key problem scenarios: (i) smooth; (ii) smooth + nonsmooth separable; (iii) asynchronous parallel; and (iv) stochastic. We illustrate empirical behavior of our algorithms by simulation experiments.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1409.2617

Authors: Reddi, Sashank, Hefny, Ahmed, Downey, Carlton, Dubey, Avinava, Sra, Suvrit

Institutions: Massachusetts Institute of Technology, Carnegie Mellon University

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Science Foundation

Award: CSR: Medium: Distributed Inference Algorithms for Machine Learning and Optimization

OpenAlex ID: W1865515570

Cites: 32

Cited by: 12

Related to: 20