Smart Predict-­‐and-­‐Optimize for Hard Combinatorial Optimization Problems

Jayanta Mandi, Emir Demirović, Peter J. Stuckey, Tias Guns

Research output: Chapter in Book/Report/Conference proceedingConference paper

36 Citations (Scopus)


Combinatorial optimization assumes that all parameters of the optimization problem, e.g. the weights in the objective function, are fixed. Often, these weights are mere estimates and increasingly machine learning techniques are used to for their estimation. Recently, Smart Predict and Optimize (SPO) has been proposed for problems with a linear objective function over the predictions, more specifically linear programming problems. It takes the regret of the predictions on the linear problem into account, by repeatedly solving it during learning. We investigate the use of SPO to solve more realistic discrete optimization problems. The main challenge is the repeated solving of the optimization problem. To this end, we investigate ways to relax the problem as well as warm-starting the learning and the solving. Our results show that even for discrete problems it often suffices to train by solving the relaxation in the SPO loss. Furthermore, this approach outperforms the state-of-the-art approach of wilder2018melding. We experiment with weighted knapsack problems as well as complex scheduling problems, and show for the first time that a predict-and-optimize approach can successfully be used on large-scale combinatorial optimization problems.
Original languageEnglish
Title of host publicationAAAI-20 Technical Tracks 2
Place of PublicationPalo Alto, California USA
PublisherAAAI Press
ChapterAAAI Technical Track on Constraint Satisfaction and Optimization
Number of pages8
ISBN (Electronic)978-1-57735-835-0
ISBN (Print)978-1-57735-835-0
Publication statusPublished - 15 Jun 2020
EventThirty-Fourth AAAI Conference on Artificial Intelligence - New York Hilton Midtown, New York, United States
Duration: 7 Feb 202012 Mar 2020

Publication series

NameAAAI-20 Technical Tracks 2
PublisherAAAI Press
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468


ConferenceThirty-Fourth AAAI Conference on Artificial Intelligence
Abbreviated titleAAAI-20
Country/TerritoryUnited States
CityNew York
Internet address


  • Optimization and Control
  • Artificial Intelligence


Dive into the research topics of 'Smart Predict-­‐and-­‐Optimize for Hard Combinatorial Optimization Problems'. Together they form a unique fingerprint.

Cite this