Independent scholarship · Open accessThe monthly digest

Indexed text attachment

parametrized-neural-networks-and-their-representations-in-differential-topology.tex

Source for Parametrized Neural Networks and Their Representations in Differential Topology

View paper · Download original file

Lines 1761–1860 of 2141. Source text is displayed literally.

1761\begin{problem}[Piecewise-linear version]\label{prob:PL}\Spg1762Prove the analogues of \cref{thm:chambers,thm:surgery} for $\relu$ networks that are generic and transversal1763in the sense of \cite{GL22}, with handle attachments replaced by the elementary moves of stratified Morse1764theory on the canonical polyhedral complex.1765\end{problem}1766 1767\begin{problem}[Quantitative discriminant]\label{prob:quant}\Spg1768For a given architecture and initialization distribution, estimate the measure of the1769$\varepsilon$-neighbourhood of the discriminant $\Delta$ of \cref{ch:decision}, and hence the expected number1770of surgeries along a path of given length. \Cref{prop:walls} suggests that $\Delta$ is a hypersurface and1771that the answer is governed by its volume.1772\end{problem}1773 1774\begin{problem}[The stack of networks]\label{prob:stack}\Spg1775For homogeneous activations, describe the quotient stack $[\Theta/G]$ of \cref{ch:symmetry} and the critical1776locus of a loss on it as a derived object, so that \cref{thm:interp} and the degeneracies listed in1777\cref{ch:loss} become statements about a single space with a virtual dimension.1778\end{problem}1779 1780Together with \cref{prob:calculus}, these are the places where the methods of the companion volume, and in1781particular its higher-categorical parts (derived manifolds, stacks, the calculus of embeddings), would be1782doing more than providing a vocabulary.1783%% ---- end ch/09-coda.tex ----1784\appendix1785%% ---- begin ch/A-dictionary.tex ----1786\chapter{Dictionary}\label{app:dictionary}1787 1788{\small1789\begin{longtable}{@{}p{0.25\textwidth}p{0.36\textwidth}p{0.29\textwidth}@{}}1790\toprule1791Network notion & Differential topology & Where\\1792\midrule1793\endhead1794architecture $F\colon\Theta\times X\to Y$ & plot of the mapping object $[X,Y]$; morphism of $\Para$ & \cref{def:family,prop:plot}\\1795composition of layers & composition of plots & \cref{def:para}\\1796weight sharing, freezing & $2$-cells of $\Para$ & \cref{exer:sharing}\\1797forward-mode derivative & tangent functor & \DT{Prop.~2.1}\\1798backpropagation & reverse derivative as a functor to lenses & \cref{thm:backprop}\\1799tangent kernel & Gram matrix $JJ^{\mathsf T}$ of the evaluation map & \cref{prop:ntk}\\1800functional dimension & rank of the realization map & \cref{def:fdim,prop:rank}\\1801permutation, sign, scaling symmetry & group of invertible $2$-cells & \cref{prop:syms}\\1802redundant hidden unit & reducible parameter; positive-dimensional fibre & \cref{prop:fibres}\\1803space of networks & quotient manifold, or stack & \cref{prop:moduli}\\1804decision boundary & preimage of a regular value & \cref{thm:boundary}\\1805multi-class boundaries & preimage of a stratification & \cref{prop:multiclass}\\1806robust topology of a classifier & chamber of the discriminant complement & \cref{thm:chambers}\\1807change of boundary topology & surgery; critical point of the trace & \cref{thm:surgery}\\1808training run, seen in input space & embedded cobordism with a Morse function & \cref{thm:trace}\\1809two runs with the same endpoints & Cerf moves & \cref{prop:moves}\\1810interpolating parameters & fibre of the evaluation map over a regular value & \cref{thm:interp}\\1811sharpness at a minimum & normal Hessian $J^{\mathsf T}J$ & \cref{prop:hess}\\1812loss barrier, mode connectivity & death level in the degree-zero barcode & \cref{prop:barrier}\\1813saturation, diverging weights & failure of properness & \cref{prop:notproper}\\1814hidden representation & immersion or embedding of the data manifold & \cref{prop:firstlayer}\\1815minimal width & invariance of domain & \cref{thm:obstruction}\\1816neural ODE & diffeotopy & \cref{prop:node}\\1817augmented neural ODE & isotopy of embeddings in the stable range & \cref{thm:augment}\\1818residual block with small branch & diffeomorphism isotopic to the identity & \cref{prop:iresnet}\\1819normalizing flow & diffeomorphism; pushforward of measures & \cref{prop:mismatch}\\1820equilibrium layer & transverse fixed point; Lefschetz count & \cref{thm:deq}\\1821\bottomrule1822\end{longtable}1823}1824%% ---- end ch/A-dictionary.tex ----1825%% ---- begin ch/B-computations.tex ----1826\chapter{Computations}\label{app:computations}1827 1828The script \texttt{verify-parametrized-networks.py} uses only the Python standard library. It implements small feedforward1829networks (widths $(2,3,1)$, $(2,4,4,1)$ and a few others) with forward evaluation, forward-mode1830differentiation by dual numbers and reverse-mode differentiation by backpropagation, a Runge--Kutta1831integrator, a Jacobi eigenvalue routine and a flood-fill component counter. It performs 49 checks in about1832three seconds, each printing \texttt{PASS} or \texttt{FAIL}, and exits with status zero if and only if all1833pass. The checks recompute the examples in the text and test numerical instances of the structural1834statements on random parameters with a fixed seed. They are not proofs, and a statement about almost every1835parameter is tested only at the parameters sampled.1836 1837{\small1838\begin{longtable}{@{}p{0.13\textwidth}p{0.79\textwidth}@{}}1839\toprule1840Chapter & What is checked\\1841\midrule1842\endhead1843\ref{ch:families} & parameter counts (\cref{exer:count}); associativity of composition in $\Para$; the1844derivative of a weight-tied network (\cref{exer:sharing}); the family $\theta+x^3$ (\cref{exer:notrich})\\1845\ref{ch:backprop} & backpropagation against forward mode and finite differences for two architectures, and1846for the input covector (\cref{thm:backprop}); the tangent kernel is positive semidefinite of rank $\rk J$;1847the output dynamics $\dot u=-K(u-y)$ (\cref{prop:ntk}); the loss gradient; the Hessian as Gauss--Newton plus1848curvature term (\cref{exer:hess})\\1849\ref{ch:symmetry} & all $48$ symmetries of the $\tanh$ network $(2,3,1)$ and the size of an orbit1850(\cref{prop:syms}); the scaling symmetry for $\relu$; rank $P=13$ at a random parameter and ranks $10$ and1851$9$ at reducible ones (\cref{thm:ident}, \cref{exer:rankdrop}); for $\relu$, the generators $\xi_j$ in1852$\ker J$ and $\rk J\le P-H$ (\cref{prop:relu}); a path of irreducible networks exchanging two hidden units1853(\cref{prop:moduli})\\1854\ref{ch:decision} & $\partial F/\partial c=1$; degenerate zeros of a one-dimensional network occur only at1855the critical values (\cref{thm:boundary}(a)); the two chambers of $x_1^2-x_2^2+c$ (\cref{exer:crossex});1856three sectors at a triple point (\cref{exer:triple}); the submersion of \cref{prop:walls}\\1857\ref{ch:paths} & component counts, critical points and indices in \cref{ex:twoblobs}; the Euler1858characteristic formula of \cref{prop:chi} for $d\le6$; the Hessian of the height function on the trace1859(\cref{exer:hessgraph}); births and deaths of boundary points on a circle (\cref{exer:d1path})\\1860\ref{ch:loss} & $\rk J=N$ and the dimension $P-N$ of the solution set; the Hessian $J^{\mathsf T}J$ with $4$