CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints

Investor logo

Warning

This publication doesn't include Faculty of Education. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

PAULUS Anselm ROLÍNEK Michal MUSIL Vít AMOS Brandon MARTIUS Georg

Year of publication 2021
Type Article in Proceedings
Conference INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139
MU Faculty or unit

Faculty of Informatics

Citation
Web https://proceedings.mlr.press/v139/paulus21a.html
Keywords machine learning; combinatorial optimization; integer linear programming; constraints
Attached files
Description Bridging logical and algorithmic reasoning with modern machine learning techniques is a fundamental challenge with potentially transformative impact. On the algorithmic side, many NP-HARD problems can be expressed as integer programs, in which the constraints play the role of their "combinatorial specification." In this work, we aim to integrate integer programming solvers into neural network architectures as layers capable of learning both the cost terms and the constraints. The resulting end-to-end trainable architectures jointly extract features from raw data and solve a suitable (learned) combinatorial problem with state-of-the-art integer programming solvers. We demonstrate the potential of such layers with an extensive performance analysis on synthetic data and with a demonstration on a competitive computer vision keypoint matching benchmark.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.