Deep reinforcement learning-based algorithms selectors for the resource scheduling in hierarchical cloud computing
Cloud computing environment is becoming increasingly complex due to its large-scale
information growth and increasing heterogeneity of computing resources. Hierarchical …
information growth and increasing heterogeneity of computing resources. Hierarchical …
Doe2vec: Deep-learning based features for exploratory landscape analysis
B van Stein, FX Long, M Frenzel, P Krause… - Proceedings of the …, 2023 - dl.acm.org
We propose DoE2Vec, a variational autoencoder (VAE)-based methodology to learn
optimization landscape characteristics for downstream meta-learning tasks, eg, automated …
optimization landscape characteristics for downstream meta-learning tasks, eg, automated …
A collection of deep learning-based feature-free approaches for characterizing single-objective continuous fitness landscapes
Exploratory Landscape Analysis is a powerful technique for numerically characterizing
landscapes of single-objective continuous optimization problems. Landscape insights are …
landscapes of single-objective continuous optimization problems. Landscape insights are …
Automated algorithm selection in single-objective continuous optimization: a comparative study of deep learning and landscape analysis methods
In recent years, feature-based automated algorithm selection using exploratory landscape
analysis has demonstrated its great potential in single-objective continuous black-box …
analysis has demonstrated its great potential in single-objective continuous black-box …
Automated algorithm selection: from feature-based to feature-free approaches
We propose a novel technique for algorithm-selection, applicable to optimisation domains in
which there is implicit sequential information encapsulated in the data, eg, in online bin …
which there is implicit sequential information encapsulated in the data, eg, in online bin …
A study on the effects of normalized TSP features for automated algorithm selection
Classic automated algorithm selection (AS) for (combinatorial) optimization problems
heavily relies on so-called instance features, ie, numerical characteristics of the problem at …
heavily relies on so-called instance features, ie, numerical characteristics of the problem at …
Deep-ELA: Deep Exploratory Landscape Analysis with Self-Supervised Pretrained Transformers for Single-and Multi-Objective Continuous Optimization Problems
In many recent works, the potential of Exploratory Landscape Analysis (ELA) features to
numerically characterize, in particular, single-objective continuous optimization problems …
numerically characterize, in particular, single-objective continuous optimization problems …
Towards feature-free automated algorithm selection for single-objective continuous black-box optimization
We propose a novel method for automated algorithm selection in the domain of single-
objective continuous black-box optimization. In contrast to existing methods, we use …
objective continuous black-box optimization. In contrast to existing methods, we use …
Exploring the feature space of TSP instances using quality diversity
Generating instances of different properties is key to algorithm selection methods that
differentiate between the performance of different solvers for a given combinatorial …
differentiate between the performance of different solvers for a given combinatorial …
Selecting fast algorithms for the capacitated vehicle routing problem with machine learning techniques
R Asín‐Achá, A Espinoza, O Goldschmidt… - …, 2024 - Wiley Online Library
We present machine learning (ML) methods for automatically selecting a “best” performing
fast algorithm for the capacitated vehicle routing problem (CVRP) with unit demands …
fast algorithm for the capacitated vehicle routing problem (CVRP) with unit demands …