Details
| Original language | English |
|---|---|
| Publication status | E-pub ahead of print - 17 Nov 2020 |
| Externally published | Yes |
Publication series
| Name | 4th Workshop on Meta-Learning at NeurIPS 2020 |
|---|
Abstract
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2020. (4th Workshop on Meta-Learning at NeurIPS 2020).
Research output: Working paper/Preprint › Preprint
}
TY - UNPB
T1 - Towards Meta-Algorithm Selection
AU - Tornede, Alexander
AU - Wever, Marcel
AU - Hüllermeier, Eyke
PY - 2020/11/17
Y1 - 2020/11/17
N2 - Instance-specific algorithm selection (AS) deals with the automatic selection of an algorithm from a fixed set of candidates most suitable for a specific instance of an algorithmic problem class, where "suitability" often refers to an algorithm's runtime. Over the past years, a plethora of algorithm selectors have been proposed. As an algorithm selector is again an algorithm solving a specific problem, the idea of algorithm selection could also be applied to AS algorithms, leading to a meta-AS approach: Given an instance, the goal is to select an algorithm selector, which is then used to select the actual algorithm for solving the problem instance. We elaborate on consequences of applying AS on a meta-level and identify possible problems. Empirically, we show that meta-algorithm-selection can indeed prove beneficial in some cases. In general, however, successful AS approaches have problems with solving the meta-level problem.
AB - Instance-specific algorithm selection (AS) deals with the automatic selection of an algorithm from a fixed set of candidates most suitable for a specific instance of an algorithmic problem class, where "suitability" often refers to an algorithm's runtime. Over the past years, a plethora of algorithm selectors have been proposed. As an algorithm selector is again an algorithm solving a specific problem, the idea of algorithm selection could also be applied to AS algorithms, leading to a meta-AS approach: Given an instance, the goal is to select an algorithm selector, which is then used to select the actual algorithm for solving the problem instance. We elaborate on consequences of applying AS on a meta-level and identify possible problems. Empirically, we show that meta-algorithm-selection can indeed prove beneficial in some cases. In general, however, successful AS approaches have problems with solving the meta-level problem.
M3 - Preprint
T3 - 4th Workshop on Meta-Learning at NeurIPS 2020
BT - Towards Meta-Algorithm Selection
ER -