Neural lattice decoders

Vincent Corlay, Joseph Boutros, Philippe Ciblat, Loic Brunel

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

Abstract

Lattice decoders constructed with neural networks are presented. Firstly, we show how the fundamental parallelotope is used as a compact set for the approximation by a neural lattice decoder. Secondly, we introduce the notion of Voronoi-reduced lattice basis. As a consequence, a first optimal neural lattice decoder is built from Boolean equations and the facets of the Voronoi cell. This decoder needs no learning. Finally, we present two neural decoders with learning. It is shown that L1 regularization and a priori information about the lattice structure lead to a simplification of the model.

Original languageEnglish
Title of host publication2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages569-573
Number of pages5
ISBN (Electronic)9781728112954
DOIs
Publication statusPublished - 20 Feb 2019
Event2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Anaheim, United States
Duration: 26 Nov 201829 Nov 2018

Publication series

Name2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings

Conference

Conference2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018
CountryUnited States
CityAnaheim
Period26/11/1829/11/18

Fingerprint

Neural networks

Keywords

  • Closest Vector Problem
  • Lattice Reduction.
  • Machine Learning
  • Neural Network

ASJC Scopus subject areas

  • Information Systems
  • Signal Processing

Cite this

Corlay, V., Boutros, J., Ciblat, P., & Brunel, L. (2019). Neural lattice decoders. In 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings (pp. 569-573). [8646560] (2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GlobalSIP.2018.8646560

Neural lattice decoders. / Corlay, Vincent; Boutros, Joseph; Ciblat, Philippe; Brunel, Loic.

2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 569-573 8646560 (2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings).

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

Corlay, V, Boutros, J, Ciblat, P & Brunel, L 2019, Neural lattice decoders. in 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings., 8646560, 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 569-573, 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018, Anaheim, United States, 26/11/18. https://doi.org/10.1109/GlobalSIP.2018.8646560
Corlay V, Boutros J, Ciblat P, Brunel L. Neural lattice decoders. In 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 569-573. 8646560. (2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings). https://doi.org/10.1109/GlobalSIP.2018.8646560
Corlay, Vincent ; Boutros, Joseph ; Ciblat, Philippe ; Brunel, Loic. / Neural lattice decoders. 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 569-573 (2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings).
@inproceedings{33ab809a38ae4825b0fec5479e9549ff,
title = "Neural lattice decoders",
abstract = "Lattice decoders constructed with neural networks are presented. Firstly, we show how the fundamental parallelotope is used as a compact set for the approximation by a neural lattice decoder. Secondly, we introduce the notion of Voronoi-reduced lattice basis. As a consequence, a first optimal neural lattice decoder is built from Boolean equations and the facets of the Voronoi cell. This decoder needs no learning. Finally, we present two neural decoders with learning. It is shown that L1 regularization and a priori information about the lattice structure lead to a simplification of the model.",
keywords = "Closest Vector Problem, Lattice Reduction., Machine Learning, Neural Network",
author = "Vincent Corlay and Joseph Boutros and Philippe Ciblat and Loic Brunel",
year = "2019",
month = "2",
day = "20",
doi = "10.1109/GlobalSIP.2018.8646560",
language = "English",
series = "2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "569--573",
booktitle = "2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings",

}

TY - GEN

T1 - Neural lattice decoders

AU - Corlay, Vincent

AU - Boutros, Joseph

AU - Ciblat, Philippe

AU - Brunel, Loic

PY - 2019/2/20

Y1 - 2019/2/20

N2 - Lattice decoders constructed with neural networks are presented. Firstly, we show how the fundamental parallelotope is used as a compact set for the approximation by a neural lattice decoder. Secondly, we introduce the notion of Voronoi-reduced lattice basis. As a consequence, a first optimal neural lattice decoder is built from Boolean equations and the facets of the Voronoi cell. This decoder needs no learning. Finally, we present two neural decoders with learning. It is shown that L1 regularization and a priori information about the lattice structure lead to a simplification of the model.

AB - Lattice decoders constructed with neural networks are presented. Firstly, we show how the fundamental parallelotope is used as a compact set for the approximation by a neural lattice decoder. Secondly, we introduce the notion of Voronoi-reduced lattice basis. As a consequence, a first optimal neural lattice decoder is built from Boolean equations and the facets of the Voronoi cell. This decoder needs no learning. Finally, we present two neural decoders with learning. It is shown that L1 regularization and a priori information about the lattice structure lead to a simplification of the model.

KW - Closest Vector Problem

KW - Lattice Reduction.

KW - Machine Learning

KW - Neural Network

UR - http://www.scopus.com/inward/record.url?scp=85063073799&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063073799&partnerID=8YFLogxK

U2 - 10.1109/GlobalSIP.2018.8646560

DO - 10.1109/GlobalSIP.2018.8646560

M3 - Conference contribution

T3 - 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings

SP - 569

EP - 573

BT - 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -