Regularized sample average approximation for high-dimensional stochastic optimization under low-rankness

Hung Yi Lee (), Charles Hernandez () and Hongcheng Liu ()
Additional contact information
Hung Yi Lee: University of Florida
Charles Hernandez: University of Florida
Hongcheng Liu: University of Florida

Journal of Global Optimization, 2023, vol. 85, issue 2, No 1, 257-282

Abstract: Abstract This paper concerns a high-dimensional stochastic programming (SP) problem of minimizing a function of expected cost with a matrix argument. To this problem, one of the most widely applied solution paradigms is the sample average approximation (SAA), which uses the average cost over sampled scenarios as a surrogate to approximate the expected cost. Traditional SAA theories require the sample size to grow rapidly when the problem dimensionality increases. Indeed, for a problem of optimizing over a p-by-p matrix, the sample complexity of the SAA is given by $${\widetilde{O}}(1)\cdot \frac{p^2}{\epsilon ^2}\cdot {polylog}(\frac{1}{\epsilon })$$ O ~ ( 1 ) · p 2 ϵ 2 · polylog ( 1 ϵ ) to achieve an $$\epsilon $$ ϵ -suboptimality gap, for some poly-logarithmic function $${polylog}(\,\cdot \,)$$ polylog ( · ) and some quantity $${\widetilde{O}}(1)$$ O ~ ( 1 ) independent of dimensionality p and sample size n. In contrast, this paper considers a regularized SAA (RSAA) with a low-rankness-inducing penalty. We demonstrate that, when the optimal solution to the SP is of low rank, the sample complexity of RSAA is $${\widetilde{O}}(1)\cdot \frac{p}{\epsilon ^3}\cdot {polylog}(p,\,\frac{1}{\epsilon })$$ O ~ ( 1 ) · p ϵ 3 · polylog ( p , 1 ϵ ) , which is almost linear in p and thus indicates a substantially lower dependence on dimensionality. Therefore, RSAA can be more advantageous than SAA especially for larger scale and higher dimensional problems. Due to the close correspondence between stochastic programming and statistical learning, our results also indicate that high-dimensional low-rank matrix recovery is possible generally beyond a linear model, even if the common assumption of restricted strong convexity is completely absent.

Keywords: Stochastic programming; Sample average approximation; Low-rankness (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10898-022-01206-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:jglopt:v:85:y:2023:i:2:d:10.1007_s10898-022-01206-3

Ordering information: This journal article can be ordered from
http://www.springer. ... search/journal/10898

DOI: 10.1007/s10898-022-01206-3

Access Statistics for this article

Journal of Global Optimization is currently edited by Sergiy Butenko

More articles in Journal of Global Optimization from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().