Abstract:Machine learning research increasingly bifurcates into two disconnected modes: benchmark-driven engineering that prioritizes metrics over understanding, and idealized theory that often fails to transfer to modern systems. In this position paper, we argue that the field focuses too heavily on these endpoints, neglecting the central scientific object: the idea. We propose an Ideas First framework in which ideas are valued for the behavioral signatures they predict in modern models, and these signatures are tested through tailored experiments designed to detect the relevant patterns rather than to win leaderboards. This shift not only bridges the gap between theory and practice but also promotes equity by removing the "complexity premium," enabling rigorous scientific contributions from researchers with modest computational, financial, and human resources. Ultimately, we advocate for a research culture centered on ideas, treating benchmarks and theorems as instruments for testing mechanistic hypotheses rather than as ends in themselves.
| Comments: | Accepted into ICML 2026 this https URL |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.15253 [cs.LG] |
| (or arXiv:2605.15253v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.15253 arXiv-issued DOI via DataCite |
From: Jairo Diaz-Rodriguez [view email]
[v1]
Thu, 14 May 2026 16:36:27 UTC (364 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。