Efficient differentiable quadratic programming layers: an ADMM approach

Andrew Butler and Roy H. Kwon ()
Additional contact information
Andrew Butler: University of Toronto
Roy H. Kwon: University of Toronto

Computational Optimization and Applications, 2023, vol. 84, issue 2, No 6, 449-476

Abstract: Abstract Recent advances in neural-network architecture allow for seamless integration of convex optimization problems as differentiable layers in an end-to-end trainable neural network. Integrating medium and large scale quadratic programs into a deep neural network architecture, however, is challenging as solving quadratic programs exactly by interior-point methods has worst-case cubic complexity in the number of variables. In this paper, we present an alternative network layer architecture based on the alternating direction method of multipliers (ADMM) that is capable of scaling to moderate sized problems with 100–1000 decision variables and thousands of training examples. Backward differentiation is performed by implicit differentiation of a customized fixed-point iteration. Simulated results demonstrate the computational advantage of the ADMM layer, which for medium scale problems is approximately an order of magnitude faster than the state-of-the-art layers. Furthermore, our novel backward-pass routine is computationally efficient in comparison to the standard approach based on unrolled differentiation or implicit differentiation of the KKT optimality conditions. We conclude with examples from portfolio optimization in the integrated prediction and optimization paradigm.

Keywords: Data driven stochastic-programming; Differentiable neural networks; Quadratic programming; ADMM (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: Track citations by RSS feed

Downloads: (external link)
http://link.springer.com/10.1007/s10589-022-00422-7 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:coopap:v:84:y:2023:i:2:d:10.1007_s10589-022-00422-7

Ordering information: This journal article can be ordered from
http://www.springer.com/math/journal/10589

DOI: 10.1007/s10589-022-00422-7

Access Statistics for this article

Computational Optimization and Applications is currently edited by William W. Hager

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