Bilel Derbel

Bilel Derbel

Auto-generated profile, based on publicly available information

Bilel Derbel

Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189 CRIStAL

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 August 2021 in Electronics
Verified
Journal Article
Open access
PDF file
KNKensuke Nakamura
Kensuke Nakamura
BDBilel Derbel
Bilel Derbel
KWKyoung Jae Won
Kyoung Jae Won
Byung-Woo HongByung-Woo Hong
Byung-Woo Hong
Deep neural networks (DNNs) have achieved great success in the last decades. DNN is optimized using the stochastic gradient descent (SGD) with learning rate annealing that overtakes the adaptive methods in many tasks. However, there is no common choice regarding the scheduled-annealing for SGD. This paper aims to present empirical analysis of learning rate annealing based on the experimental results using the major data-sets on the image classification that is one of the key applications of the DNNs. Our experiment involves recent deep neural network models in combination with a variety of learning rate annealing methods. We also propose an annealing combining the sigmoid function with warmup that is shown to overtake both the adaptive methods and the other existing schedules in accuracy in most cases with DNNs.

12 July 2023
Verified
Conference Paper
Open access
ALArnaud Liefooghe
Arnaud Liefooghe
GOGabriela Ochoa
Gabriela Ochoa
SVSébastien Verel
Sébastien Verel
BDBilel Derbel
Bilel Derbel
The structure of local optima in multi-objective combinatorial optimization and their impact on algorithm performance are not yet properly understood. In this paper, we are interested in the representation of multi-objective landscapes and their multi-modality. More specifically, we revise and extend the network of Pareto local optimal solutions (PLOS-net), inspired by the well-established local optima network from single-objective optimization. We first define a compressed PLOS-net which allows us to enhance its perception while preserving the important notion of connectedness between local optima. We then study an alternative visualization of the (compressed) PLOS-net that focuses on good-quality solutions, improves the distinction between connected components in the network, and generalizes well to landscapes with more than 2 objectives. We finally define a number of network metrics that characterize the PLOS-net, some of them being strongly correlated with search performance. We visualize and experiment with small-size multiobjective nk-landscapes, and we disclose the effect of PLOS-net metrics against well-established multi-objective local search and evolutionary algorithms.

9 March 2017 in Lecture Notes in Computer Science
Verified
Book Chapter
Closed access
PDF file
ALArnaud Liefooghe
Arnaud Liefooghe
BDBilel Derbel
Bilel Derbel
SVSébastien Verel
Sébastien Verel
HAHernán Aguirre
Hernán Aguirre
KTKiyoshi Tanaka
Kiyoshi Tanaka

9 April 2020
Verified
Book Chapter
Closed access
PDF file
GPGeoffrey Pruvost
Geoffrey Pruvost
BDBilel Derbel
Bilel Derbel
ALArnaud Liefooghe
Arnaud Liefooghe
Ke LiKe Li
Ke Li
QZQingfu Zhang
Qingfu Zhang

8 July 2022
Verified
Conference Paper
Open access
RCRaphaël Cosson
Raphaël Cosson
RSRoberto Santana
Roberto Santana
BDBilel Derbel
Bilel Derbel
ALArnaud Liefooghe
Arnaud Liefooghe
So far, multi-objective NK landscapes have been investigated under the assumption of a homogeneous nature of the involved objectives in terms of difficulty. However, we argue that problems with heterogeneous objectives, e.g., in terms of multi-modality, can be challenging for multi-objective evolutionary algorithms, and deserve further considerations. In this paper, we propose a model of multi-objective NK landscapes, where each objective has a different degree of variable interactions (K), as a benchmark to investigate heterogeneous multi-objective optimization problems. We show that the use of a rank-annotated neighborhood network with labeled local optimal solutions, together with landscape metrics extracted from the heterogeneous objectives, thoroughly characterize bi-objective NK landscapes with a different level of heterogeneity among the objectives.

7 September 2024
Verified
Book Chapter
Closed access
PDF file
Zakaria Abdelmoiz DahiZakaria Abdelmoiz Dahi
Zakaria Abdelmoiz Dahi
FCFrancisco Chicano
Francisco Chicano
Gabriel LuqueGabriel Luque
Gabriel Luque
BDBilel Derbel
Bilel Derbel
Enrique AlbaEnrique Alba
Enrique Alba