Abstract:Automated algorithm selection for continuous black-box optimization depends on representing problem information under limited probing and selecting solvers under heavy-tailed performance distributions. This paper proposes a geometric probing framework that represents each problem instance by randomly sampled multi-scale two-dimensional slices of the objective landscape. The slices are encoded with validity-mask-aware visual pooling and aggregated into an instance representation. Solver selection is then performed by a logarithmic composite score combining a learned instance-conditioned estimate with an algorithm-side empirical prior.
The framework is evaluated on a standard single-objective black-box optimization benchmark suite with a portfolio of twelve solvers under instance-level, grouped random, and problem-level transfer protocols. Under the two within-suite protocols, it reduces aggregate mean relative expected running time from 30.37 for the single best solver to 3.14 and 3.61, while also improving median and upper-tail performance. Under problem-level transfer, the canonical adaptive setting improves typical and moderate-tail performance but leaves the mean dominated by rare extreme failures; a prior-heavy scoring variant mitigates this failure mode, although its robustness may be benchmark-dependent. The results suggest that coarse geometric probes provide useful solver-relevant information, while robust cross-problem selection also depends on metric-aligned decision scoring.
| Comments: | 20 pages, 9 figures, 6 tables; extended version of a GECCO 2026 poster-track paper; code available at this https URL |
| Subjects: | Machine Learning (cs.LG); Optimization and Control (math.OC) |
| Cite as: | arXiv:2604.09095 [cs.LG] |
| (or arXiv:2604.09095v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.09095 arXiv-issued DOI via DataCite |
From: Jiabao Brad Wang [view email]
[v1]
Fri, 10 Apr 2026 08:24:37 UTC (21,488 KB)
[v2]
Tue, 14 Apr 2026 02:07:35 UTC (21,488 KB)
[v3]
Thu, 21 May 2026 16:13:41 UTC (20,646 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。