跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2605.04946 · v3

Training-Time Batch Normalization Reshapes Local Partition Geometry in Piecewise-Affine Networks

首次提交 2026-05-06 22:14
版本更新 2026-11-16 17:33
雷达观测 2026-11-17 17:11
arXiv ↗PDF ↗

摘要

The effect of batch normalization (BN) on the function realized during training is less understood than its effect on optimization. We study training-time BN in continuous piecewise-affine (CPA) networks through the affine regions they induce in local ℓ∞\ell_\infty windows around the data. Conditioned on a mini-batch, every switching hyperplane of a BN layer with learned parameters and a general CPA activation is a translate of a hyperplane through the batch centroid, at an offset given by a standardized quantity times the batch spread, independent of the raw bias. We prove an exact formula, valid under general position, for the number of regions in a window in terms of window cuts and interior intersections. For a BN layer it gives a lower bound on the local count in terms of the standardized offsets; the bound depends on the batch only through its spread and not on the biases or the batch location. Without BN the best such bound is 11: for any weights and batch, some biases leave the window as a single region. We prove that the formula holds in deeper layers, inside parent affine regions of any rank. By the exact formula, BN increases the expected local count whenever it increases the expected numbers of window cuts and of interior intersections, which we examine empirically. Offset distributions of networks trained on synthetic data, MNIST, CIFAR-10 and TinyImageNet show higher window-cut rates under BN, and exact enumeration in two dimensions attributes most of the additional BN regions to interior intersections.

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

本站首次收录为 v3,暂无更早版本可对照。

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。

v3 · 2026-11-16 17:33 · 最新观测版本

Training-Time Batch Normalization Reshapes Local Partition Geometry in Piecewise-Affine Networks

The effect of batch normalization (BN) on the function realized during training is less understood than its effect on optimization. We study training-time BN in continuous piecewise-affine (CPA) networks through the affine regions they induce in local ℓ∞\ell_\infty windows around the data. Conditioned on a mini-batch, every switching hyperplane of a BN layer with learned parameters and a general CPA activation is a translate of a hyperplane through the batch centroid, at an offset given by a standardized quantity times the batch spread, independent of the raw bias. We prove an exact formula, valid under general position, for the number of regions in a window in terms of window cuts and interior intersections. For a BN layer it gives a lower bound on the local count in terms of the standardized offsets; the bound depends on the batch only through its spread and not on the biases or the batch location. Without BN the best such bound is 11: for any weights and batch, some biases leave the window as a single region. We prove that the formula holds in deeper layers, inside parent affine regions of any rank. By the exact formula, BN increases the expected local count whenever it increases the expected numbers of window cuts and of interior intersections, which we examine empirically. Offset distributions of networks trained on synthetic data, MNIST, CIFAR-10 and TinyImageNet show higher window-cut rates under BN, and exact enumeration in two dimensions attributes most of the additional BN regions to interior intersections.

查看此版本解读 →查看此版本原文 ↗