Paper Detail

Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection

Sijie Li, Shanda Li, Haowei Lin, Weiwei Sun, Ameet Talwalkar, Yiming Yang

arxiv Score 4.3

Published 2026-04-24 · First seen 2026-04-27

General AI

Abstract

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{li2026spend,
  title = {Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection},
  author = {Sijie Li and Shanda Li and Haowei Lin and Weiwei Sun and Ameet Talwalkar and Yiming Yang},
  year = {2026},
  abstract = {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 extr},
  url = {https://arxiv.org/abs/2604.22753},
  keywords = {cs.LG},
  eprint = {2604.22753},
  archiveprefix = {arXiv},
}

Metadata

{}