GPU 云租赁价格基准在缺失观测下的稳健性评估
Robustness Evaluation of GPU Cloud Pricing Benchmarks under Incomplete Observations: A Controlled Missingness Study
AI 导读
一项 arXiv 研究(arXiv:2611.17796)压力测试了固定等权中位数规则在 GPU 云租赁价格报价缺失时的表现,涵盖 27 种场景、190 个留出日期上的 5,800 次 Monte Carlo 模拟。
正文 · 原文
Abstract:Daily GPU rental-price benchmarks can fail when marketplace quotes are missing. This article stress-tests a fixed equal-weight median rule under four imposed masking mechanisms and four benchmark-level recovery methods. Across 5,800 Monte Carlo realisations in 27 scenarios on 190 held-out days, whole-source outages reduce publication coverage to 0.77 while preserving zero conditional error on published dates; composition-changing loss retains 0.86 coverage but produces 7.74 log points of error. A separate past-only stratum-level ablation reduces error by 4.15 to 6.70 log points in five composition-changing cases, using a richer information set. An observable-signal withholding rule improves the primary error-coverage criterion in 0 of 10 cases. Results concern observed asking-price measurements, not transaction prices or identified real-world missingness mechanisms.
| Comments: | 5 pages, 3 figures, 7 tables |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.17796 [cs.AI] |
| (or arXiv:2611.17796v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.17796 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jooya Wong [view email]
[v1]
Fri, 13 Nov 2026 06:18:24 UTC (540 KB)
来源:arXiv cs.AI · arxiv.org