跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.25867 · v1

Full Rank and Stable Sampling of $\tanh$ Networks

首次提交 2026-11-19 18:18
版本更新 2026-11-19 18:18
雷达观测 2026-11-20 19:57
arXiv ↗PDF ↗

摘要

We study the recovery of feedforward tanh⁡\tanh networks of fixed architecture with PP parameters from finitely many point evaluations. First, we characterize the set of parameters where the differential of the realization map has full rank and show that it coincides with the regular parameters in the sense of Vla{č}i{ć} and B{ö}lcskei (2021). Second, we make use of this characterization to prove that almost every tuple of 2P+12P+1 sampling points yields uniform-norm Lipschitz stability on compact subsets of this parameter set. Third, we prove that for exact observations, projected gradient descent and projected Gauss--Newton converge locally from sufficiently close feasible initial guesses. The same evaluations also determine the realized function for arbitrary parameters and identify parameters in the characterized set up to permutations and sign changes of hidden neurons. Finally, we develop a general framework for real-analytic networks that highlights the role of full rank in stability and local reconstruction.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-19 18:18 · 最新观测版本

Full Rank and Stable Sampling of $\tanh$ Networks

We study the recovery of feedforward tanh⁡\tanh networks of fixed architecture with PP parameters from finitely many point evaluations. First, we characterize the set of parameters where the differential of the realization map has full rank and show that it coincides with the regular parameters in the sense of Vla{č}i{ć} and B{ö}lcskei (2021). Second, we make use of this characterization to prove that almost every tuple of 2P+12P+1 sampling points yields uniform-norm Lipschitz stability on compact subsets of this parameter set. Third, we prove that for exact observations, projected gradient descent and projected Gauss--Newton converge locally from sufficiently close feasible initial guesses. The same evaluations also determine the realized function for arbitrary parameters and identify parameters in the characterized set up to permutations and sign changes of hidden neurons. Finally, we develop a general framework for real-analytic networks that highlights the role of full rank in stability and local reconstruction.

查看此版本解读 →查看此版本原文 ↗