A singular Riemannian geometry approach to Deep Neural Networks I. Theoretical foundations

• URL: http://arxiv.org/abs/2201.09656v2
• Date: Fri, 23 Sep 2022 10:19:09 GMT
• Title: A singular Riemannian geometry approach to Deep Neural Networks I. Theoretical foundations
• Authors: Alessandro Benfenati and Alessio Marta
• Abstract summary: Deep Neural Networks are widely used for solving complex problems in several scientific areas, such as speech recognition, machine translation, image analysis. We study a particular sequence of maps between manifold, with the last manifold of the sequence equipped with a Riemannian metric. We investigate the theoretical properties of the maps of such sequence, eventually we focus on the case of maps between implementing neural networks of practical interest.
• Score: 77.86290991564829
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep Neural Networks are widely used for solving complex problems in several scientific areas, such as speech recognition, machine translation, image analysis. The strategies employed to investigate their theoretical properties mainly rely on Euclidean geometry, but in the last years new approaches based on Riemannian geometry have been developed. Motivated by some open problems, we study a particular sequence of maps between manifolds, with the last manifold of the sequence equipped with a Riemannian metric. We investigate the structures induced trough pullbacks on the other manifolds of the sequence and on some related quotients. In particular, we show that the pullbacks of the final Riemannian metric to any manifolds of the sequence is a degenerate Riemannian metric inducing a structure of pseudometric space, we show that the Kolmogorov quotient of this pseudometric space yields a smooth manifold, which is the base space of a particular vertical bundle. We investigate the theoretical properties of the maps of such sequence, eventually we focus on the case of maps between manifolds implementing neural networks of practical interest and we present some applications of the geometric framework we introduced in the first part of the paper.

Related papers

• The geometry of the deep linear network [0.0]
  Rigorous results by several authors are unified into a thermodynamic framework for deep learning. Several links between the DLN and other areas of mathematics are discussed, along with some open questions.
  arXiv  Detail & Related papers  (2024-11-13T20:15:50Z)
• RMLR: Extending Multinomial Logistic Regression into General Geometries [64.16104856124029]
  Our framework only requires minimal geometric properties, thus exhibiting broad applicability. We develop five families of SPD MLRs under five types of power-deformed metrics. On rotation matrices we propose Lie MLR based on the popular bi-invariant metric.
  arXiv  Detail & Related papers  (2024-09-28T18:38:21Z)
• A singular Riemannian Geometry Approach to Deep Neural Networks III. Piecewise Differentiable Layers and Random Walks on $n$-dimensional Classes [49.32130498861987]
  We study the case of non-differentiable activation functions, such as ReLU. Two recent works introduced a geometric framework to study neural networks. We illustrate our findings with some numerical experiments on classification of images and thermodynamic problems.
  arXiv  Detail & Related papers  (2024-04-09T08:11:46Z)
• Gaussian Entanglement Measure: Applications to Multipartite Entanglement of Graph States and Bosonic Field Theory [50.24983453990065]
  An entanglement measure based on the Fubini-Study metric has been recently introduced by Cocchiarella and co-workers. We present the Gaussian Entanglement Measure (GEM), a generalization of geometric entanglement measure for multimode Gaussian states. By providing a computable multipartite entanglement measure for systems with a large number of degrees of freedom, we show that our definition can be used to obtain insights into a free bosonic field theory.
  arXiv  Detail & Related papers  (2024-01-31T15:50:50Z)
• Riemannian Residual Neural Networks [58.925132597945634]
  We show how to extend the residual neural network (ResNet) ResNets have become ubiquitous in machine learning due to their beneficial learning properties, excellent empirical results, and easy-to-incorporate nature when building varied neural networks.
  arXiv  Detail & Related papers  (2023-10-16T02:12:32Z)
• On Geometric Connections of Embedded and Quotient Geometries in Riemannian Fixed-rank Matrix Optimization [5.876141028192136]
  This paper proposes a general procedure for establishing the geometric landscape connections of a Riemannian optimization problem under the embedded and quotient geometries. We observe an algorithmic connection between two geometries with some specific Riemannian metrics in fixed-rank matrix optimization. Results provide a few new theoretical insights to unanswered questions in the literature.
  arXiv  Detail & Related papers  (2021-10-23T03:13:56Z)
• Semi-Riemannian Graph Convolutional Networks [36.09315878397234]
  We develop a principled Semi-Riemannian GCN that first models data in semi-Riemannian manifold of constant nonzero curvature. Our method provides a geometric inductive bias that is sufficiently flexible to model mixed heterogeneous topologies like hierarchical graphs with cycles.
  arXiv  Detail & Related papers  (2021-06-06T14:23:34Z)
• A Unifying and Canonical Description of Measure-Preserving Diffusions [60.59592461429012]
  A complete recipe of measure-preserving diffusions in Euclidean space was recently derived unifying several MCMC algorithms into a single framework. We develop a geometric theory that improves and generalises this construction to any manifold.
  arXiv  Detail & Related papers  (2021-05-06T17:36:55Z)
• Nested Grassmannians for Dimensionality Reduction with Applications [7.106986689736826]
  We propose a novel framework for constructing a nested sequence of homogeneous Riemannian manifold. We focus on applying the proposed framework to the Grassmann manifold, giving rise to the nested Grassmannians (NG) Specifically, each planar (2D) shape can be represented as a point in the complex projective space which is a complex Grass-mann manifold. With the proposed NG structure, we develop algorithms for the supervised and unsupervised dimensionality reduction problems respectively.
  arXiv  Detail & Related papers  (2020-10-27T20:09:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.