CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F21%3A00122671" target="_blank" >RIV/00216224:14330/21:00122671 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints
Original language 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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/EF18_053%2F0016952" target="_blank" >EF18_053/0016952: Postdoc2MUNI</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 38th International Conference on Machine Learning
ISBN
—
ISSN
2640-3498
e-ISSN
—
Number of pages
11
Pages from-to
8443-8453
Publisher name
PMLR
Place of publication
Neuvedeno
Event location
Online
Event date
Jul 18, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—