# Which Geometry on Which Layer? A Principled Criterion for Mixed-Optimizer Training

Canonical HTML: https://hiroki11x.github.io/ja/publications/which-geometry-on-which-layer/

- 著者: Hiroki Naganuma, Laura Gomezjurado Gonzalez, Mahdi Ghaznavi, Atsushi Nitanda, Ioannis Mitliagkas, Seng Pei Liew, Ryuichiro Hataya
- 掲載先: Under Review
- 日付: 2026-05
- 研究領域: [スケーラブルな事前学習と分散学習](https://hiroki11x.github.io/ja/research/#scalable-pretraining) · [機械学習の最適化](https://hiroki11x.github.io/ja/research/#optimization)

## 概要

概要は原文リンクをご覧ください。

## 一次資料