Content Gazette - May 2019 - 27

Non-Convex Optimization for Signal Processing
and Machine Learning
Special Issue for IEEE Signal Processing Magazine
Call for Papers
Motivation
Optimization is now widely reckoned as an indispensable tool in signal processing and machine learning.
Although convex optimization remains a powerful, and is by far the most extensively used, paradigm for
tackling signal processing and machine learning applications, we have witnessed a shift in interest to nonconvex optimization techniques over the last few years. On one hand, many signal processing and machine
learning applications-such as dictionary recovery, low-rank matrix recovery, phase retrieval, and source
localization-give rise to well-structured non-convex formulations that exhibit properties akin to those of
convex optimization problems and can be solved to optimality more efficiently than their convex reformulations or approximations. On the other hand, for some contemporary signal processing and machine learning
applications-such as deep learning and sparse regression-the use of convex optimization techniques may not
be adequate or even desirable. Given the rapidly-growing yet scattered literature on the subject, there is a
clear need for a special issue that introduces the essential elements of non-convex optimization to the broader
signal processing and machine learning communities, provides insights into how structures of the non-convex
formulations of various practical problems can be exploited in algorithm design, showcases some notable successes in this line of study, and identifies important research issues that are motivated by existing or emerging
applications. This special issue aims to address the aforementioned needs by soliciting tutorial-style articles
with pointers to available software whenever possible. Topics of interest include, but are not limited to
* optimization fundamentals, including algorithm design and analysis techniques for generic and structured problems (e.g., difference-of-convex optimization, mixed-integer optimization, non-convex nonLipschitz optimization, non-convex non-smooth optimization), parallel and distributed non-convex methods, and software toolboxes
* big data analytics
* blind demixing and deconvolution
* computer vision and image processing applications
* deep learning
* localization
* massive MIMO
* phase retrieval
* statistical estimation
* structured matrix/tensor decomposition, such as low-rank matrix recovery and non-negative matrix/tensor
factorization, with applications
To enhance readability and appeal for a broad audience, prospective authors are encouraged to use an
intuitive approach in their presentation; e.g., by using simple instructive examples, considering special cases
that show insights into the ideas, and using illustrations as far as practicable.
Submission Procedure
Prospective authors should submit their white papers through the ScholarOne ManuscriptsTM system at
https://mc.manuscriptcentral.com/spmag-ieee. Further guidelines and information on paper submission
can be found at https://signalprocessingsociety.org/publications-resources/submit-manuscript.
Schedule
*
*
*
*
*
*
*
*

White paper due: August 1, 2019
Invitation notification: September 1, 2019
Manuscript due: November 1, 2019
First review to authors: January 1, 2020
Revision due: March 1, 2020
Acceptance notification: May 1, 2020
Final manuscript due: June 1, 2020
Publication date: September 1, 2020

Guest Editors
Anthony Man-Cho So, The Chinese University of Hong Kong, manchoso@se.cuhk.edu.hk
Prateek Jain, Microsoft Research India, prajain@microsoft.com
Wing-Kin Ma, The Chinese University of Hong Kong, wkma@ee.cuhk.edu.hk
Gesualdo Scutari, Purdue University, gscutari@purdue.edu

www.signalprocessingsociety.org

[27]

MAY 2019
https://mc.manuscriptcentral.com/spmag-ieee https://www.signalprocessingsociety.org/publications-resources/submit-manuscript http://www.signalprocessingsociety.org
Content Gazette - May 2019

Table of Contents for the Digital Edition of Content Gazette - May 2019
