广义 Orlicz 范数下 $L^\infty$ 泛函的逼近
神经与进化计算
2024-08-12 v2
摘要
本文旨在处理当下界增长率趋向无穷时广义 Orlicz 范数的渐近行为。在 mild 凸性假设下,本文证明了广义 Orlicz 能量序列的 -收敛结果及相关表示定理,可表述为 泛函。该文指出,后者假设在变指数情形下被移除。
引用
@article{arxiv.2406.16506,
title = {Natural Gradient Interpretation of Rank-One Update in CMA-ES},
author = {Ryoki Hamano and Shinichi Shirakawa and Masahiro Nomura},
journal= {arXiv preprint arXiv:2406.16506},
year = {2024}
}
备注
This paper has been accepted for presentation at PPSN2024. Updated experimental results and related sentences in Sections 6 and 7