English
Related papers

Related papers: Geodesics in the Deep Linear Network

200 papers

A complete understanding of the widely used over-parameterized deep networks is a key step for AI. In this work we try to give a geometric picture of over-parameterized deep networks using our geometrization scheme. We show that the…

Machine Learning · Computer Science 2019-02-12 Xiao Dong , Ling Zhou

In the paper we consider the linear underdetermined system of a special type. Systems of this type appear in non-homogeneous network flow programming problems in the form of systems of constraints and can be characterized as systems with a…

Optimization and Control · Mathematics 2008-07-04 Ludmila Pilipchuk , Eugene Vecharynski

Understanding the inner workings of neural networks, including transformers, remains one of the most challenging puzzles in machine learning. This study introduces a novel approach by applying the principles of gauge symmetries, a key…

Machine Learning · Computer Science 2024-02-06 Koji Hashimoto , Yuji Hirono , Akiyoshi Sannai

We classify maximal totally geodesic submanifolds in exceptional symmetric spaces up to isometry. Moreover, we introduce an invariant for certain totally geodesic embeddings of semisimple symmetric spaces, which we call the Dynkin index. We…

Differential Geometry · Mathematics 2023-02-24 Andreas Kollross , Alberto Rodríguez-Vázquez

We provide an easy approach to the geodesic distance on the general linear group GL(n) for left-invariant Riemannian metrics which are also right-O(n)-invariant. The parametrization of geodesic curves and the global existence of length…

Differential Geometry · Mathematics 2016-02-18 Robert Martin , Patrizio Neff

Feature descriptors play a crucial role in a wide range of geometry analysis and processing applications, including shape correspondence, retrieval, and segmentation. In this paper, we introduce Geodesic Convolutional Neural Networks…

Computer Vision and Pattern Recognition · Computer Science 2018-06-11 Jonathan Masci , Davide Boscaini , Michael M. Bronstein , Pierre Vandergheynst

We consider the Dirichlet-to-Neumann operator and the direct and inverse Calder\'on's mappings appearing in the Inverse Problem of recovering a smooth bounded and positive isotropic conductivity of a material filling a smooth bounded domain…

Analysis of PDEs · Mathematics 2024-04-16 Javier Castro , Claudio Muñoz , Nicolás Valenzuela

The paper is devoted to the study of geodesic orbit Riemannian spaces that could be characterize by the property that any geodesic is an orbit of a 1-parameter group of isometries. In particular, we discuss some important totally geodesic…

Differential Geometry · Mathematics 2017-10-24 Yu. G. Nikonorov

We give a formal procedure for computing preimages of convolutional network outputs using the dual basis defined from the set of hyperplanes associated with the layers of the network. We point out the special symmetry associated with…

Machine Learning · Computer Science 2019-05-23 Stefan Carlsson

Continuous-depth neural networks, such as Neural ODEs, have refashioned the understanding of residual neural networks in terms of non-linear vector-valued optimal control problems. The common solution is to use the adjoint sensitivity…

Machine Learning · Computer Science 2022-02-16 Andrew Corbett , Dmitry Kangin

The paper surveys open problems and questions related to geodesics defined by Riemannian, Finsler, semi Riemannian and magnetic structures on manifolds.

Differential Geometry · Mathematics 2021-02-03 Keith Burns , Vladimir S. Matveev

Non-Euclidean data is frequently encountered across different fields, yet there is limited literature that addresses the fundamental challenge of training neural networks with manifold representations as outputs. We introduce the trick…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Tongtong Zhang , Xian Wei , Yuanxiang Li

How to understand deep learning systems remains an open problem. In this paper we propose that the answer may lie in the geometrization of deep networks. Geometrization is a bridge to connect physics, geometry, deep network and quantum…

Machine Learning · Computer Science 2019-01-15 Xiao Dong , Ling Zhou

We consider the nonlinear problem of determining a connection and a Higgs field from the corresponding parallel transport along geodesics on a Riemannian manifold with boundary, in any dimension. The problem can be reduced to an integral…

Analysis of PDEs · Mathematics 2016-10-18 Hanming Zhou

The last decade has witnessed an experimental revolution in data science and machine learning, epitomised by deep learning methods. Indeed, many high-dimensional learning tasks previously thought to be beyond reach -- such as computer…

Machine Learning · Computer Science 2021-05-04 Michael M. Bronstein , Joan Bruna , Taco Cohen , Petar Veličković

In this article we classify totally geodesic submanifolds of homogeneous nearly K\"ahler 6-manifolds, and of the G2-cones over these 6-manifolds. To this end, we develop new techniques for the study of totally geodesic submanifolds of…

Differential Geometry · Mathematics 2025-06-10 Juan Manuel Lorenzo-Naveiro , Alberto Rodríguez-Vázquez

In this second paper on the method of deriving linearizing transformations for nonlinear ODEs, we extend the method to a set of two coupled second order nonlinear ODEs. We show that besides the conventional point, Sundman and generalized…

Exactly Solvable and Integrable Systems · Physics 2012-01-27 V. K. Chandrasekar , M. Senthilvelan , M. Lakshmanan

We investigate the connections between the differential-geometric properties of the exponential map from the space of real skew symmetric matrices onto the group of real special orthogonal matrices and the manifold of real orthogonal…

Differential Geometry · Mathematics 2016-11-03 Alberto Dolcetti , Donato Pertici

In the present paper we show that the geodesic flows of a sub-Riemannian metric and that of a Riemannian extension commute if and only if the extended metric is parallel with respect to a certain connection. This helps us to describe the…

Differential Geometry · Mathematics 2015-02-24 Mauricio Godoy Molina , Erlend Grong

We classify generalized Wallach spaces which are g.o. spaces. We also investigate homogeneous geodesics in generalized Wallach spaces for any given invariant Riemannian metric and we give some examples.

Differential Geometry · Mathematics 2017-09-07 Andreas Arvanitoyeorgos , Yu Wang
‹ Prev 1 4 5 6 7 8 10 Next ›