English
Related papers

Related papers: The Alexander-Hirschowitz theorem for neurovarieti…

200 papers

This paper is devoted to the estimation of the Lipschitz constant of general neural network architectures using semidefinite programming. For this purpose, we interpret neural networks as time-varying dynamical systems, where the $k$-th…

Machine Learning · Computer Science 2024-11-26 Patricia Pauli , Dennis Gramlich , Frank Allgöwer

We present a simple proof for the universality of invariant and equivariant tensorized graph neural networks. Our approach considers a restricted intermediate hypothetical model named Graph Homomorphism Model to reach the universality…

Machine Learning · Computer Science 2019-10-10 Takanori Maehara , Hoang NT

We propose, and illustrate via a neural network example, two different approaches to coarse-graining large heterogeneous networks. Both approaches are inspired from, and use tools developed in, methods for uncertainty quantification in…

Adaptation and Self-Organizing Systems · Physics 2016-11-03 Minseok Choi , Tom Bertalan , Carlo R. Laing , Ioannis G. Kevrekidis

We initiate the study of the inherent tradeoffs between the size of a neural network and its robustness, as measured by its Lipschitz constant. We make a precise conjecture that, for any Lipschitz activation function and for most datasets,…

Machine Learning · Computer Science 2020-11-26 Sébastien Bubeck , Yuanzhi Li , Dheeraj Nagaraj

Properties of the Alexander polynomials of Hurwitz curves are investigated. A complete description of the set of the Alexander polynomials of irreducible Hurwitz curves in the terms of their roots is given.

Symplectic Geometry · Mathematics 2007-05-23 Vik. S. Kulikov

We give sharp lower bounds for the degree of the syzygies involving the partial derivatives of a homogeneous polynomial defining a nodal hypersurface. The result gives information on the position of the singularities of a nodal hypersurface…

Algebraic Geometry · Mathematics 2011-11-23 Alexandru Dimca , Gabriel Sticlaru

The outage performance of wireless networks with unstructured network topologies is investigated. The network reliability perspective of graph theory is used to obtain the network outage polynomial of generalized wireless networks by…

Information Theory · Computer Science 2019-04-30 Semiha Tedik Basaran , Gunes Karabulut Kurt , Frank R. Kschischang

We introduce a flexible setup allowing for a neural network to learn both its size and topology during the course of a standard gradient-based training. The resulting network has the structure of a graph tailored to the particular learning…

Machine Learning · Computer Science 2020-07-16 Romuald A. Janik , Aleksandra Nowak

We analyze the data-dependent capacity of neural networks and assess anomalies in inputs from the perspective of networks during inference. The notion of data-dependent capacity allows for analyzing the knowledge base of a model populated…

Machine Learning · Computer Science 2023-04-13 Jinsol Lee , Charlie Lehman , Mohit Prabhushankar , Ghassan AlRegib

We define a GL-variety to be a (typically infinite dimensional) algebraic variety equipped with an action of the infinite general linear group under which the coordinate ring forms a polynomial representation. Such varieties have been used…

Algebraic Geometry · Mathematics 2022-09-07 Arthur Bik , Jan Draisma , Rob H. Eggermont , Andrew Snowden

The paper uses statistical and differential geometric motivation to acquire prior information about the learning capability of an artificial neural network on a given dataset. The paper considers a broad class of neural networks with…

Machine Learning · Computer Science 2020-12-02 Ankan Dutta , Arnab Rakshit

Polynomial Neural Networks (PNNs) possess a rich algebraic and geometric structure. However, their identifiability -- a key property for ensuring interpretability -- remains poorly understood. In this work, we present a comprehensive…

Machine Learning · Computer Science 2026-02-03 Konstantin Usevich , Ricardo Borsoi , Clara Dérand , Marianne Clausel

We develop global pluripotential theory in the setting of Berkovich geometry over a trivially valued field. Specifically, we define and study functions and measures of finite energy and the non-Archimedean Monge-Ampere operator on any…

Algebraic Geometry · Mathematics 2022-03-24 Sébastien Boucksom , Mattias Jonsson

Using neural networks to solve variational problems, and other scientific machine learning tasks, has been limited by a lack of consistency and an inability to exactly integrate expressions involving neural network architectures. We address…

Machine Learning · Computer Science 2021-10-28 Jonas A. Actor , Andy Huang , Nathaniel Trask

It is known that the Alexander polynomial detects fibered knots and 3-manifolds that fiber over the circle. In this note, we show that when the Alexander polynomial becomes inconclusive, the notion of "knot adjacency", studied in the paper…

Geometric Topology · Mathematics 2008-03-23 Efstratia Kalfagianni , Xiao-Song Lin

We introduce a new threshold model of social networks, in which the nodes influenced by their neighbours can adopt one out of several alternatives. We characterize social networks for which adoption of a product by the whole network is…

Social and Information Networks · Computer Science 2015-03-20 Krzysztof R. Apt , Evangelos Markakis

With the development of neural networks based machine learning and their usage in mission critical applications, voices are rising against the \textit{black box} aspect of neural networks as it becomes crucial to understand their limits and…

Machine Learning · Statistics 2017-08-08 El Mahdi El Mhamdi , Rachid Guerraoui , Sebastien Rouault

In this paper we generalize the Ritt-Kolchin method of characteristic sets and the classical Gr\"obner basis technique to prove the existence and obtain methods of computation of multivariate difference-differential dimension polynomials…

Commutative Algebra · Mathematics 2012-07-20 Alexander Levin

Reliable generalization lies at the heart of safe ML and AI. However, understanding when and how neural networks generalize remains one of the most important unsolved problems in the field. In this work, we conduct an extensive empirical…

In this work we introduce a new multiscale artificial neural network based on the structure of $\mathcal{H}$-matrices. This network generalizes the latter to the nonlinear case by introducing a local deep neural network at each spatial…

Numerical Analysis · Mathematics 2019-11-12 Yuwei Fan , Lin Lin , Lexing Ying , Leonardo Zepeda-Nunez