A new perspective on low-rank optimization
Name
10107_2023_Article_1933.pdf
Size
845.72 KB
Format
Adobe PDF
Checksum (MD5)
21639f011dadc7a765ccd32f8f712062
Author(s)
Bertsimas, Dimitris
Cory-Wright, Ryan
Pauphilet, Jean
Date Issued
February 18, 2023
Publisher
Springer Berlin Heidelberg
Citation
Bertsimas, Dimitris, Cory-Wright, Ryan and Pauphilet, Jean. 2023. "A new perspective on low-rank optimization."
Version
Final published version
Abstract
Abstract
A key question in many low-rank problems throughout optimization, machine learning, and statistics is to characterize the convex hulls of simple low-rank sets and judiciously apply these convex hulls to obtain strong yet computationally tractable relaxations. We invoke the matrix perspective function—the matrix analog of the perspective function—to characterize explicitly the convex hull of epigraphs of simple matrix convex functions under low-rank constraints. Further, we combine the matrix perspective function with orthogonal projection matrices–the matrix analog of binary variables which capture the row-space of a matrix–to develop a matrix perspective reformulation technique that reliably obtains strong relaxations for a variety of low-rank problems, including reduced rank regression, non-negative matrix factorization, and factor analysis. Moreover, we establish that these relaxations can be modeled via semidefinite constraints and thus optimized over tractably. The proposed approach parallels and generalizes the perspective reformulation technique in mixed-integer optimization and leads to new relaxations for a broad class of problems.
MIT Department
Sloan School of Management
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/s10107-023-01933-9
