# Preprint reports lower-compute method for LLM scaling laws

_Friday, September 4, 2026 at 12:00 AM EDT · Science · Latest · Tier 2 — Notable_

A preprint describes Power-Law Entropy Search, a multi-fidelity Bayesian-optimization method designed to estimate how optimal LLM-training hyperparameters change with model and data scale. The authors tested it on synthetic benchmarks, surrogates fitted to real LLM training data and LLM pre-training runs, reporting accurate estimates with less than one-tenth the compute budget of grid search and other baselines. The results have not been peer reviewed.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2609.01431)

---
Canonical: https://techandbusiness.org/newswire/a0QtEU-JD7MoZXj-G1sw1N
Retrieved: 2026-09-04T17:34:37.331Z
Publisher: Tech & Business (techandbusiness.org)