# Meta 提出 Skaling law 耦合规模与数据

- 来源：elvis (@omarsar0)
- 发布时间：2026-08-11 00:03
- AIHOT 分数：36
- AIHOT 链接：https://aihot.virxact.com/items/cmsnfmfrq059nrohf3zdfo8jo
- 原文链接：https://x.com/omarsar0/status/2086845790983716917

## AI 摘要

Meta 新论文提出 Skaling law，通过单一交互指数耦合模型容量与训练数据，将平均绝对百分比误差在插值与外推场景下降低 1.5x 至 3x。该定律在数据稀缺和过度训练区间修正了标准 Chinchilla 与 Kaplan 形式的偏差，并可用约 10 倍更少算力从稀疏网格外推完整训练配置。

## 正文

Impressive new paper from Meta.

(bookmark it)

Scaling laws assume model size and training data act on loss independently.

This work introduces Skaling law, which couples capacity and data through a single interaction exponent. The extra term cuts mean absolute percentage error by 1.5x to 3x across both interpolation and extrapolation.

The largest corrections land in the data-scarce and heavy-overtraining regimes where the standard Chinchilla and Kaplan forms drift.

Paired with a sparse grid restricted to low-compute runs, it extrapolates the full grid using roughly 10x less compute than a uniform sweep.

Why does it matter?

Deployment now happens well past compute optimal. A law that stays accurate there, and that can be fit from small runs, changes how a pretraining budget gets planned.

Paper: https://arxiv.org/abs/2608.07222

Track more trending AI papers in our academy: https://academy.dair.ai/