Saved in:
Bibliographic Details
Main Authors: Li, Sijie, Li, Shanda, Lin, Haowei, Sun, Weiwei, Talwalkar, Ameet, Yang, Yiming
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.22753
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908991227953152
author Li, Sijie
Li, Shanda
Lin, Haowei
Sun, Weiwei
Talwalkar, Ameet
Yang, Yiming
author_facet Li, Sijie
Li, Shanda
Lin, Haowei
Sun, Weiwei
Talwalkar, Ameet
Yang, Yiming
contents Scaling laws are used to plan multi-million-dollar training runs, but fitting those laws can itself cost millions. In modern large-scale workflows, assembling a sufficiently informative set of pilot experiments is already a major budget-allocation problem rather than a routine preprocessing step. We formulate scaling-law fitting as budget-aware sequential experimental design: given a finite pool of runnable experiments with heterogeneous costs, choose which runs to execute so as to maximize extrapolation accuracy in a high-cost target region. We then propose an uncertainty-aware method for sequentially allocating experimental budget toward the runs most useful for target-region extrapolation. Across a diverse benchmark of scaling-law tasks, our method consistently outperforms classical design-based baselines, and often approaches the performance of fitting on the full experimental set while using only about 10% of the total training budget. Our code is available at https://github.com/PlanarG/active-sl.
format Preprint
id arxiv_https___arxiv_org_abs_2604_22753
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection
Li, Sijie
Li, Shanda
Lin, Haowei
Sun, Weiwei
Talwalkar, Ameet
Yang, Yiming
Machine Learning
Scaling laws are used to plan multi-million-dollar training runs, but fitting those laws can itself cost millions. In modern large-scale workflows, assembling a sufficiently informative set of pilot experiments is already a major budget-allocation problem rather than a routine preprocessing step. We formulate scaling-law fitting as budget-aware sequential experimental design: given a finite pool of runnable experiments with heterogeneous costs, choose which runs to execute so as to maximize extrapolation accuracy in a high-cost target region. We then propose an uncertainty-aware method for sequentially allocating experimental budget toward the runs most useful for target-region extrapolation. Across a diverse benchmark of scaling-law tasks, our method consistently outperforms classical design-based baselines, and often approaches the performance of fitting on the full experimental set while using only about 10% of the total training budget. Our code is available at https://github.com/PlanarG/active-sl.
title Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection
topic Machine Learning
url https://arxiv.org/abs/2604.22753