Independent scholarship · Open accessThe monthly digest

Indexed text attachment

representation-theory-of-parametrized-neural-models-on-spaces.tex

Source for Representation Theory of Parametrized Neural Models on Spaces

View paper · Download original file

Lines 181–280 of 1343. Source text is displayed literally.

181slice. A shared parameter $P$ can be imposed by reparametrization along182the diagonal $P\to P\times_B P$. More general tying is expressed by a183map $P\to\prod_{i,B}P_i$ into the product of layer parameters.184 185\begin{theorem}[Relative representation and descent]186\label{thm:relative-representation}187The $\infty$-category of layers from $X$ to $Y$ is188$\E_{/[X,Y]_B}$. On these categories, series composition is189induced by internal composition of exponentials and respects190reparametrizations. The construction commutes with pullback in $B$.191For an effective epimorphism $U\to B$ with \v{C}ech nerve $U_\bullet$,192the global layer category is equivalent to193\begin{equation}194 \label{eq:layerdescent}195 \lim_{[n]\in\boldsymbol\Delta}196   \E_{/[X_n,Y_n]_{U_n}},197 \qquad X_n=X\times_B U_n,\quad Y_n=Y\times_B U_n .198\end{equation}199\end{theorem}200 201\begin{proof}202Currying yields the equivalence of mapping spaces203\[204 \Map_B(P\times_B X,Y)\simeq\Map_B(P,[X,Y]_B).205\]206It is natural in $P$. The two definitions of a morphism of207layers therefore give the same homotopy fiber of a map of mapping208spaces, including its higher simplices. The relative double slice209$(\overB)_{/[X,Y]_B}$ is $\E_{/[X,Y]_B}$.210 211Evaluation in series transposes to a morphism212\[213 [X,Y]_B\times_B[Y,Z]_B\longrightarrow [X,Z]_B.214\]215It sends the classifying maps of the two layers to the classifying216map of their composite. The identity is classified by the transpose217of $\id_X$ with parameter $B$. The associativity and unit218compatibilities follow by uncurrying the iterated compositions.219Both ways to combine a string yield evaluation in the same order220on the product of its parameters. All product comparisons come221from their limit universal properties.222 223Let $a:C\to B$. If $T\to C$, the left adjoint $a_!$ to $a^*$224is composition of structure maps. Using the pullback identification225$a_!(T\times_C a^*X)\simeq (a_!T)\times_B X$ gives226\begin{align*}227 \Map_C(T,a^*[X,Y]_B)228 &\simeq \Map_B(a_!T,[X,Y]_B)\\229 &\simeq \Map_B(a_!T\times_B X,Y)\\230 &\simeq \Map_C(T\times_C a^*X,a^*Y).231\end{align*}232By Yoneda these equivalences identify $a^*[X,Y]_B$233with $[a^*X,a^*Y]_C$, preserving evaluation. Pullback also234preserves the products that define series composition.235 236Finally, the effective epimorphism is the colimit of its237\v{C}ech nerve. Colimits in an $\infty$-topos satisfy descent for238slices \cite[\S6.1.3]{lurie-htt}. Hence $\overB$ is the limit of the239categories $\E_{/U_n}$. Taking the slice at the compatible240exponential commutes with this limit, since a slice is the241category of arrows with fixed target. Base change identifies242the local targets with the ones in \eqref{eq:layerdescent}.243\end{proof}244 245\begin{figure}[tbp]246\centering247\(248\begin{tikzcd}[column sep=2.4em,row sep=2.0em]249  P\times_B X \arrow[r,"f"] \arrow[d,"u\times_B\id_X"'] &250  Y \arrow[d,equal] \\251  Q\times_B X \arrow[r,"g"'] & Y252\end{tikzcd}253\)254\caption{A reparametrization includes a commuting comparison of255evaluations. In an $\infty$-topos the comparison is a specified homotopy.}256\label{fig:reparam}257\end{figure}258 259A point of $[X,Y]_B$ over $b$ is one evaluation on the fibers.260The classifying map retains a distinction between a space of these261evaluations and a space of weights mapping into it. An architecture262selects a classifying map, for instance by composing affine maps,263an equivariant convolution, and a nonlinearity. The ambient264exponential also includes maps that the selected architecture265cannot realize.266 267\subsection{Transport and actions}268 269In spaces, straightening identifies $\Spc_{/B}$ with270$\Fun(B,\Spc)$, where the base $B$ is regarded as an271$\infty$-groupoid. Transport acts by equivalences and the slice272exponential is computed fiberwise \cite[\S3.2]{lurie-htt}. For273a path $\gamma:b\to c$ with transports $t_X,t_Y$, exponentials274transport by $h\mapsto t_Y h t_X^{-1}$. A classifying map275is consequently a coherent family of maps276$P_b\to [X_b,Y_b]$ commuting with transport. For an ordinary277action of an abstract group $G$ on $P,X,Y$, the resulting278comparison reads279\begin{equation}280 \label{eq:equiv-eval}