Independent scholarship · Open accessThe monthly digest

Indexed text attachment

differential-topology-of-parametrized-neural-networks.tex

Source for Differential Topology of Parametrized Neural Networks

View paper · Download original file

Lines 14–113 of 1074. Source text is displayed literally.

14\usepackage{caption}15\usepackage{booktabs,balance}16\usepackage{xurl}17\usepackage{hyperref}18\usepackage{bookmark}19 20\definecolor{paperink}{HTML}{202824}21\definecolor{paperaccent}{HTML}{145A51}22\definecolor{papermuted}{HTML}{51655F}23\definecolor{paperrule}{HTML}{B6CBC4}24\hypersetup{25  pdftitle={Differential Topology of Parametrized Neural Networks},26  pdfsubject={Jet representations, decision boundaries, and reconstruction},27  colorlinks=true,linkcolor=paperaccent,citecolor=paperaccent,urlcolor=paperaccent28}29\AtBeginDocument{\color{paperink}}30\setlength{\columnsep}{.29in}31\setlength{\parindent}{1em}32\setlength{\parskip}{1pt plus .5pt}33\setlength{\emergencystretch}{1.7em}34\linespread{1.035}35\allowdisplaybreaks[1]36\raggedbottom37\clubpenalty=100038\widowpenalty=100039 40\titleformat{\section}{\large\bfseries\raggedright}41  {\color{paperaccent}\thesection}{.55em}{}42\titlespacing*{\section}{0pt}{14pt plus 3pt minus 2pt}{5pt}43\titleformat{\subsection}{\normalsize\bfseries\raggedright}44  {\color{paperaccent}\thesubsection}{.55em}{}45\titlespacing*{\subsection}{0pt}{10pt plus 2pt minus 1pt}{4pt}46\captionsetup{font=small,labelfont={bf,color=paperaccent}}47 48\pagestyle{fancy}49\fancyhf{}50\fancyhead[L]{\footnotesize\sffamily\color{papermuted}Differential topology of parametrized neural networks}51\fancyfoot[R]{\footnotesize\sffamily\color{papermuted}\thepage}52\renewcommand{\headrulewidth}{0pt}53\fancypagestyle{plain}{%54  \fancyhf{}%55  \fancyfoot[R]{\footnotesize\sffamily\color{papermuted}\thepage}%56  \renewcommand{\headrulewidth}{0pt}%57}58 59\theoremstyle{plain}60\newtheorem{theorem}{Theorem}[section]61\newtheorem{proposition}[theorem]{Proposition}62\newtheorem{lemma}[theorem]{Lemma}63\newtheorem{corollary}[theorem]{Corollary}64\theoremstyle{definition}65\newtheorem{definition}[theorem]{Definition}66\newtheorem{example}[theorem]{Example}67\theoremstyle{remark}68\newtheorem{remark}[theorem]{Remark}69\DeclareMathOperator{\Map}{Map}70\DeclareMathOperator{\Tot}{Tot}71\DeclareMathOperator{\Fun}{Fun}72\DeclareMathOperator{\Hom}{Hom}73\DeclareMathOperator{\grad}{grad}74\DeclareMathOperator{\Ext}{Ext}75\DeclareMathOperator{\Res}{Res}76\DeclareMathOperator{\Kl}{Kl}77\DeclareMathOperator{\id}{id}78\DeclareMathOperator{\rank}{rank}79\newcommand{\E}{\mathcal E}80\newcommand{\Spc}{\mathcal S}81\newcommand{\R}{\mathbb R}82\newcommand{\C}{\mathbb C}83\newcommand{\Z}{\mathbb Z}84\newcommand{\overB}{\E_{/B}}85\tikzcdset{every label/.append style={font=\small}}86\begin{document}87\twocolumn[88\begin{@twocolumnfalse}89\noindent\textcolor{paperaccent}{\rule{\textwidth}{1pt}}\par90\vspace{11pt}91{\noindent\fontsize{27}{32}\selectfont\bfseries92Differential Topology of\\Parametrized Neural Networks\par}93\vspace{8pt}94{\noindent\large\color{papermuted}95Jet representations, decision boundaries, and reconstruction\par}96\vspace{10pt}97{\noindent\small November 2026\par}98\vspace{9pt}99\noindent\begin{minipage}{\textwidth}\small100\textbf{Abstract.}101A smooth neural architecture represents a space of weights by evaluations102on a data manifold. We give architecture-level conditions for controlling103first jets, decision boundaries, and reconstruction. An affine readout of104immersed features is submersive on first jets, while an arbitrary smooth105feature map with free final biases still gives generic transverse106classification boundaries. We compute a fold discriminant for a107quadratic readout on the circle and a regular family whose decision108boundaries have nontrivial monodromy. For equivariant layers the109stabilizer representation can force an excess intersection even when110the total evaluation is submersive. An explicit torus calculation111exhibits the associated obstruction complex. For autoencoders, exact112ambient recovery requires an embedding, and a spherical example gives113a sharp uniform error bound below the required latent dimension.