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 1263–1343 of 1343. Source text is displayed literally.

1263The circle decoder makes that distinction visible without1264changing the input or output law. For each specialization1265the relevant structures enter explicitly: a smooth site1266for smooth realizations, a probability interpretation for1267sampling, and a compact unitary action for the Hilbert1268decomposition.1269\par1270\begin{thebibliography}{99}1271\small\raggedright1272 1273\bibitem{amari}1274S.-i. Amari. Natural gradient works efficiently in learning.1275\emph{Neural Computation} 10(2), 251--276, 1998.1276\href{https://doi.org/10.1162/089976698300017746}{DOI}.1277 1278\bibitem{reprbook}1279Anonymous. \emph{Representation Theory in Higher Categories:1280From Compact Harmonic Analysis to Coherent Group Actions}.1281Higher Categorical Semantics, 2026. Chapters 2--4, 17--18, 20, and 27--28.1282\href{https://higher-categorical-semantics.pages.dev/research/representation-theory-in-higher-categories-1d29df27}{Published edition}.1283 1284\bibitem{ay-jost-le-schwachhoefer-2015}1285N. Ay, J. Jost, H. V. L\^e, and L. Schwachh\"ofer.1286Information geometry and sufficient statistics.1287\emph{Probability Theory and Related Fields} 162, 327--364, 2015.1288\href{https://doi.org/10.1007/s00440-014-0574-8}{DOI}.1289 1290\bibitem{cohen-geiger-weiler}1291T. S. Cohen, M. Geiger, and M. Weiler.1292A general theory of equivariant CNNs on homogeneous spaces.1293\emph{Advances in Neural Information Processing Systems} 32, 2019.1294\href{https://proceedings.neurips.cc/paper_files/paper/2019/hash/b9cfe8b6042cf759dc4c0cccb27a6737-Abstract.html}{Proceedings}.1295 1296\bibitem{cruttwell}1297G. S. H. Cruttwell, B. Gavranovi\'c, N. Ghani, P. Wilson, and F. Zanasi.1298Categorical foundations of gradient-based learning.1299In \emph{Programming Languages and Systems}, ESOP 2022.1300\href{https://doi.org/10.1007/978-3-030-99336-8_1}{DOI}.1301 1302\bibitem{fong-spivak-tuyeras}1303B. Fong, D. I. Spivak, and R. Tuy\'eras.1304Backprop as functor: A compositional perspective on supervised learning.1305In \emph{Proceedings of LICS}, 2019.1306\href{https://hdl.handle.net/1721.1/123513}{Author manuscript}.1307 1308\bibitem{fritz-2020}1309T. Fritz. A synthetic approach to Markov kernels, conditional1310independence and theorems on sufficient statistics.1311\emph{Advances in Mathematics} 370, 107239, 2020.1312\href{https://doi.org/10.1016/j.aim.2020.107239}{DOI}.1313 1314\bibitem{hatcher-vbkt}1315A. Hatcher. \emph{Vector Bundles and K-Theory}. Version 2.2, 2017.1316\href{https://pi.math.cornell.edu/~hatcher/VBKT/VBpage.html}{Author's notes}.1317 1318\bibitem{kottke-lam}1319C. Kottke. \emph{Linear Analysis on Manifolds}.1320Notes for Math 7376, 2016.1321\href{https://ckottke.ncf.edu/neu/7376_sp16/lacm.pdf}{Lecture notes}.1322 1323\bibitem{lurie-ha}1324J. Lurie. \emph{Higher Algebra}. Manuscript, 2017.1325\href{https://www.math.ias.edu/~lurie/papers/HA.pdf}{Author's manuscript}.1326 1327\bibitem{lurie-htt}1328J. Lurie. \emph{Higher Topos Theory}. Annals of Mathematics Studies 170.1329Princeton University Press, 2009.1330\href{https://www.math.ias.edu/~lurie/papers/HTT.pdf}{Author's copy}.1331 1332\bibitem{stacks-quotients}1333The Stacks Project Authors. \emph{The Stacks Project}, section on1334quotients by group actions.1335\href{https://stacks.math.columbia.edu/tag/04UV}{Tag 04UV}.1336 1337\bibitem{watanabe-2009}1338S. Watanabe. \emph{Algebraic Geometry and Statistical Learning Theory}.1339Cambridge University Press, 2009.1340\href{https://doi.org/10.1017/CBO9780511800474}{DOI}.1341\end{thebibliography}1342\end{document}1343