The Algorithm Selection Problem

Rice, John R.

doi:10.1016/s0065-2458(08)60520-3

Cited by 847 publications

(559 citation statements)

References 8 publications

Supporting

Mentioning

548

Contrasting

Unclassified

Order By: Relevance

“…EPMs for predicting the "empirical hardness" of instances have their origin a decade ago [15] and have been the preferred core reasoning tool of early state-of-the-art methods for the algorithm selection problem (which aim to select the best algorithm for a given problem, dependent on its features [16,17,18]), in particular of early iterations of the SATzilla algorithm selector for SAT [19]. Since then, these predictive models have been extended to model the dependency of performance on (often categorical) algorithm parameters, to make probabilistic predictions, and to work effectively with large amounts of training data [20,11,21,12,22].…”

Section: Empirical Performance Modelsmentioning

confidence: 99%

Identifying Key Algorithm Parameters and Instance Features Using Forward Selection

Hutter

Hoos

Leyton‐Brown

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Most state-of-the-art algorithms for large scale optimization expose free parameters, giving rise to combinatorial spaces of possible configurations. Typically, these spaces are hard for humans to understand. In this work, we study a model-based approach for identifying a small set of both algorithm parameters and instance features that suffices for predicting empirical algorithm performance well. Our empirical analyses on a wide variety of hard combinatorial problem benchmarks (spanning SAT, MIP, and TSP) show that-for parameter configurations sampled uniformly at random-very good performance predictions can typically be obtained based on just two key parameters, and that similarly, few instance features and algorithm parameters suffice to predict the most salient algorithm performance characteristics in the combined configuration/feature space. We also use these models to identify settings of these key parameters that are predicted to achieve the best overall performance, both on average across instances and in an instance-specific way. This serves as a further way of evaluating model quality and also provides a tool for further understanding the parameter space. We provide software for carrying out this analysis on arbitrary problem domains and hope that it will help algorithm developers gain insights into the key parameters of their algorithms, the key features of their instances, and their interactions.

show abstract

Section: Empirical Performance Modelsmentioning

confidence: 99%

Identifying Key Algorithm Parameters and Instance Features Using Forward Selection

Hutter

Hoos

Leyton‐Brown

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The issue of selecting the right algorithm has been the subject of many studies over the past 20 years [17,3,23,20,19]. Most approaches rely on the concept of metalearning.…”

Section: Background and Motivationmentioning

confidence: 99%

“…ensembles) and often have many parameters that greatly influence their performance. This yields a whole spectrum of methods and their variations, so that testing all possible candidates on the given problem, e.g., using cross-validation, quickly becomes prohibitively expensive.The issue of selecting the right algorithm has been the subject of many studies over the past 20 years [17,3,23,20,19]. Most approaches rely on the concept of metalearning.…”

mentioning

confidence: 99%

Selecting Classification Algorithms with Active Testing

Leite

Brazdil

Vanschoren³

2012

Machine Learning and Data Mining in Pattern Recognition

View full text Add to dashboard Cite

“…Algorithm selection is the problem of selecting the most efficient algorithm among equivalent ones for a given problem instance (Rice, 1976). In its original form, algorithm selection involves only a one-shot decision-the "best" algorithm is selected and then applied to the instance with no further decision making.…”

Section: Learning To Select Branching Rulesmentioning

confidence: 99%

Learning to Select Branching Rules in the DPLL Procedure for Satisfiability

Lagoudakis

Littman

2001

Electronic Notes in Discrete Mathematics

View full text Add to dashboard Cite

The DPLL procedure is the most popular complete satisfiability (SAT) solver. While its worst case complexity is exponential, the actual running time is greatly affected by the ordering of branch variables during the search. Several branching rules have been proposed, but none is the best in all cases. This work investigates the use of automated methods for choosing the most appropriate branching rule at each node in the search tree. We consider a reinforcementlearning approach where a value function, which predicts the performance of each branching rule in each case, is learned through trial runs on a typical problem set of the target class of SAT problems. Our results indicate that, provided sufficient training on a given class, the resulting strategy performs as well as (and, in some cases, better than) the best branching rule for that class.

show abstract

The Algorithm Selection Problem

Cited by 847 publications

References 8 publications

Identifying Key Algorithm Parameters and Instance Features Using Forward Selection

Identifying Key Algorithm Parameters and Instance Features Using Forward Selection

Selecting Classification Algorithms with Active Testing

Learning to Select Branching Rules in the DPLL Procedure for Satisfiability

Contact Info

Product

Resources

About