arXiv:2608. 11859v1 Announce Type: new Abstract: Scaling laws promised cost-effective experiments; six years later, they have yet to fully deliver.
By Nicholas Lourie, Kyunghyun Cho, Karen Ullrich, Sanae Lotfi
arXiv:2602. 10545v2 Announce Type: replace-cross Abstract: Modern large-scale neural networks are often trained and released in multiple sizes to accommodate diverse inference budgets.
By Yuxin Ma, Nan Chen, Mateo D\'iaz, Soufiane Hayou, Dmitriy Kunisky, Soledad Villar
The paper proposes a framework to reduce the cost of constructing scaling laws for large foundation models by treating data collection as a Bayesian optimization problem. It shows that expanding the compute budget progressively and augmenting observed configurations with surrogate-fantasized evaluations can recover a broad experimental grid, enabling accurate scaling law fitting without training every configuration. This approach can achieve computational savings of up to 10–100× compared to a full dense grid.
By Abhash Kumar Jha, Diana Alexandra Onu\c{t}u, Neeratyoy Mallik, Swagatam Haldar, Sam Laing, Niccol\`o Ajroldi, Shiwei Liu, Joaquin Vanschoren, Aaron Klein
The paper introduces Power‑Law Entropy Search (PLES), a computational‑cost‑aware acquisition function that uses multi‑fidelity Bayesian optimization to efficiently estimate optimal hyperparameter scaling laws for large language model training. PLES focuses on reducing the overall uncertainty of scaling law estimates rather than optimizing a single objective, selecting configurations that maximize uncertainty reduction per unit computational cost. Experiments on synthetic benchmarks, surrogate models, and real LLM pre‑training runs show that PLES converges to accurate scaling laws using less than one‑tenth of the computational budget required by conventional grid search and other baselines.
By Zhiliang Chen, Sebastian Ament, David Eriksson, Maximilian Balandat, Eytan Bakshy, Jihao Andreas Lin
The paper introduces a new closed‑form scaling law that extends Chinchilla’s original formula to handle data‑constrained regimes. It decomposes loss into undercapacity, undertraining, and overfitting components, saturating between an irreducible loss and an uninformed baseline. The authors validate the model on diverse architectures and domains, achieving state‑of‑the‑art RMSE across multiple LLM scaling‑law grids and enabling cost‑aware training allocations.
By Christopher M. Bryant, Hao Liu
The paper investigates the often-overlooked scale vectors in large language models, showing that despite their tiny size they are crucial for pre‑training performance. The authors provide theoretical insights that scale vectors mainly aid optimization rather than expressivity, and they analyze how weight decay affects different normalization layers. Building on these findings, they propose lightweight improvements—branch‑specific heterogeneity, better placement, and magnitude‑direction reparameterization—that consistently reduce loss across a range of model sizes and training settings.
By Mingze Wang, Shuchen Zhu, Yuxin Fang, Binghui Li, Kai Shen, Shu Zhong