Multi-objective parameter configuration of machine learning algorithms using model-based optimization
Authors:
- 1 December 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
The performance of many machine learning algorithms heavily depends on the setting of their respective hyperparameters. Many different tuning approaches exist, from simple grid or random search approaches to evolutionary algorithms and Bayesian optimization. Often, these algorithms are used to optimize a single performance criterion. But in practical applications, a single criterion may not be sufficient to adequately characterize the behavior of the machine learning method under consideration and the Pareto front of multiple criteria has to be considered. We propose to use model-based multi-objective optimization to efficiently approximate such Pareto fronts.Keywords
This publication has 23 references indexed in Scilit:
- A Case Study on Multi-Criteria Optimization of an Event Detection Software under Limited Budgets2013
- Tuning and evolution of support vector kernelsEvolutionary Intelligence, 2012
- A Simple Approach to Emulation for Computer Models With Qualitative and Quantitative FactorsTechnometrics, 2011
- Surrogate-assisted evolutionary computation: Recent advances and future challengesSwarm and Evolutionary Computation, 2011
- Sequential Model-Based Optimization for General Algorithm Configuration2011
- The Attainment-Function Approach to Stochastic Multiobjective Optimizer Assessment and Comparison2010
- Multiobjective Optimization on a Limited Budget of Evaluations Using Model-Assisted $\mathcal{S}$ -Metric Selection2008
- Multi-class ROC analysis from a multi-objective optimisation perspectivePattern Recognition Letters, 2006
- A fast and elitist multiobjective genetic algorithm: NSGA-IIIEEE Transactions on Evolutionary Computation, 2002
- A General Coefficient of Similarity and Some of Its Properties1971