Experimental Methods for the Analysis of Optimization Algorithms

By Thomas Bartz-Beielstein, Marco Chiarandini, Lus Paquete, Mike Preuss. 2010

374 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/89def107c3780399324af8226e20f10ecc619d59

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Industrial and Manufacturing Engineering

Citations in the corpus

Iterated Greedy methods for the distributed permutation flowshop scheduling problem (2019, background): “The interested reader can refer to504 Bartz-Beielstein et al. (2010) for a detailed description of far more advanced505 methodologies.506 507 Detailed ANOVA tables are omitted due to space considerations.”
Feature-based tuning of simulated annealing applied to the curriculum-based course timetabling problem (2014, methodology): “The first involved running a F-Race(RSD) tuning (Birattari et al., 2010) over the training instances with a 95% confidence, in order to establish a baseline for further comparisons.”
A survey on new generation metaheuristic algorithms (2019, methodology): “More information about the experimental methodologies, the statistical evaluations, and parameter tuning of metaheuristics can be found in (McGeoch, 2001; Birattari and Kacprzyk, 2009; Bartz-Beielstein et al., 2010).”
Parameter tuning for configuring and analyzing evolutionary algorithms (2011, background): “The difference between two types of parameters has already been noted in evolutionary computing, but various authors use various naming conventions.”
Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges (2021, methodology): “The iterated racing (IR, Birattari et al., 2010) procedure is a general algorithm configuration method that optimizes for a configuration of a general (not necessarily ML) algorithm that performs well over a given distribution of (arbitrary) problems.”
Algorithm runtime prediction: Methods & evaluation (2012, methodology): “Because the problems have been considered by substantially different communities, we separately consider related work on predicting the runtime of parameterless and parameterized algorithms, and applications of these predictions to gain insights into instance hardness and algorithm parameters.”