et de Développements en Intelligence Artificielle

2004

Citations in the corpus

Efficient Benchmarking of Hyperparameter Optimizers via Surrogates (2015, methodology): “The methods most commonly used in practice are manual search and grid search, but recently, it was shown that even simple random search can yield much better results (Balaprakash, Birattari, and Stützle 2007; Bergstra and Bengio 2012).”
Automated Configuration of Mixed Integer Programming Solvers (2010, unknown): “Some relatively recent model-free approaches permit both larger numbers of parameters and categorical domains, in particular Composer [12], F-Race [9, 8], GGA [3], and our own ParamILS [20, 19].”
Sequential Model-Based Optimization for General Algorithm Configuration (2011, methodology): “The most prominent configuration methods are the racing algorithm F-RACE [5] and our own iterated local search algorithm PARAMILS [7, 8].”
Swarm robotics: a review from the swarm engineering perspective (2013, methodology): “Massink et al. (2012) used Bio-PEPA to analyze consensus achievement in a robot swarm.”
A Survey of Automatic Parameter Tuning Methods for Metaheuristics (2020, methodology): “Yuan et al. [34] broadly considered black-box optimization algorithms as sampling methods for parameter tuning.”
Parameter tuning for configuring and analyzing evolutionary algorithms (2011, methodology): “Approaches designed for finding the best possible parameter vector are enhanced with features that provide more information about robustness (such as REVAC [33]), while approaches from the informative type are improved for delivering high performing parameter-values (such as I/F-RACE [39] and CALIBR”
Auto-WEKA : combined selection and hyperparameter optimization of supervised machine learning algorithms (2014, background): “Iterated F-Race [I/F-Race; Balaprakash et al., 2007] belongs to the more general family of model-based optimization algorithms, and as the name suggests, uses a racing procedure at its core.”
Automated Algorithm Configuration and Parameter Tuning (2012, methodology): “…for each configuration to be sampled, first, one of the Ni is chosen using a rank-based probabilistic selection scheme based on the performance of the configuration ci associated with Ni (for details, see Balaprakash et al, 2007), and then, a configuration is sampled from this distribution.”