Cited By
View all- Richoux FBaffier J(2023)Automatic error function learning with interpretable compositional networksAnnals of Mathematics and Artificial Intelligence10.1007/s10472-022-09829-8Online publication date: 20-Feb-2023
Error function learning with interpretable compositional networks for constraint-based local search
Pages 137 - 138
Abstract
In Constraint Programming, some Constraint-Based Local Search algorithms exploit error functions, a finer representation of constraints than the usual one. However, this makes problem modeling significantly harder, since providing a set of error functions is not always easy. Here, we propose a method to automatically learn an error function corresponding to a constraint. Our method learns error functions upon a variant of neural networks we named Interpretable Compositional Networks, allowing us to get interpretable results, unlike regular artificial neural networks. Experiments show that our method can learn, over small-dimensional spaces or incomplete spaces, functions that scale on high-dimensional spaces.
Supplementary Material
p137-richoux_suppl.pdf
- Download
- 104.29 KB
References
[1]
Frederic Boussemart, Christophe Lecoutre, Gilles Audemard, and Cédric Piette. 2016. XCSP3: An Integrated Format for Benchmarking Combinatorial Constrained Problems. arXiv e-prints abs/1611.03398 (2016), 1--238.
[2]
Frank Hutter, Holger H. Hoos, Kevin Leyton-Brown, and Thomas Stützle. 2009. ParamILS: An Automatic Algorithm Configuration Framework. Journal of Artificial Intelligence Research 36 (2009), 267--306.
[3]
Maarten Keijzer, J. J. Merelo, G. Romero, and M. Schoenauer. 2002. Evolving Objects: A General Purpose Evolutionary Computation Library. Artificial Evolution 2310 (2002), 829--888.
[4]
Florian Richoux and Jean-François Baffier. 2021. Error Function Learning with Interpretable Compositional Networks for Constraint-Based Local Search. arXiv e-prints abs/2002.09811 (2021), 1--11.
[5]
Kenneth O. Stanley. 2007. Compositional Pattern Producing Networks: A Novel Abstraction of Development. Genetic Programming and Evolvable Machines 8, 2 (2007), 131--162.
Index Terms
- Error function learning with interpretable compositional networks for constraint-based local search
Recommendations
A constraint-based local search backend for MiniZinc
MiniZinc is a modelling language for combinatorial problems, which can then be solved by a solver provided in a backend. There are many backends, based on technologies such as constraint programming, integer programming, or Boolean satisfiability ...
Averaged learning equations of error-function-based multilayer perceptrons
The multilayer perceptrons (MLPs) have strange behaviors in the learning process caused by the existing singularities in the parameter space. A detailed theoretical or numerical analysis of the MLPs is difficult due to the non-integrability of the ...
A Java library for Constraint-Based Local Search: Application to the master thesis defense timetabling problem
SoICT '15: Proceedings of the 6th International Symposium on Information and Communication TechnologyConstraint-Based Local Search (CBLS) is an architecture for local search that uses constraints and objectives to control the local search. CBLS has many advantages in designing and implementing local search programs such as compositionality, modularity ...
Comments
Information & Contributors
Information
Published In
July 2021
2047 pages
Copyright © 2021 Owner/Author.
Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 08 July 2021
Check for updates
Author Tags
Qualifiers
- Poster
Conference
GECCO '21
Sponsor:
Acceptance Rates
Overall Acceptance Rate 1,669 of 4,410 submissions, 38%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 43Total Downloads
- Downloads (Last 12 months)2
- Downloads (Last 6 weeks)0
Reflects downloads up to 02 Feb 2025
Other Metrics
Citations
Cited By
View all- Richoux FBaffier J(2023)Automatic error function learning with interpretable compositional networksAnnals of Mathematics and Artificial Intelligence10.1007/s10472-022-09829-8Online publication date: 20-Feb-2023
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in