paper-with-me

Papers

Quantitative Flow Approximation Properties of Narrow Neural ODEs

2025-03-06 · Karthik Elamvazhuthi

In this note, we revisit the problem of flow approximation properties of neural ordinary differential equations (NODEs). The approximation properties have been considered as a flow controllability problem in recent literature. The neural ODE is considered {\it narrow} when the parameters have dimension equal to the input of the neural network, and hence have limited width. We derive the relation of narrow NODEs in approximating flows of shallow but wide NODEs. Due to existing results on approximation properties of shallow neural networks, this facilitates understanding which kind of flows of dynamical systems can be approximated using narrow neural ODEs. While approximation properties of narrow NODEs have been established in literature, the proofs often involve extensive constructions or require invoking deep controllability theorems from control theory. In this paper, we provide a simpler proof technique that involves only ideas from ODEs and Gr{\"o}nwall's lemma. Moreover, we provide an estimate on the number of switches needed for the time dependent weights of the narrow NODE to mimic the behavior of a NODE with a single layer wide neural network as the velocity field.

📄 PDF Abstract BibTeX arXiv:2503.04068

Code (0)

등록된 구현이 없습니다.

Tasks

LEMMA

Methods 이 논문이 사용한 방법론

NODE Neural Oblivious Decision Ensembles (NODE) is a tabular data architecture that consists of differentiable oblivious decision trees (ODT) that are trained end-to-end by…

Similar Papers 제목 키워드 기반

Approximation properties of neural ODEs

2025-03-19 · Arturo De Marinis, Davide Murari, Elena Celledoni, Nicola Guglielmi 외

We study the approximation properties of shallow neural networks whose activation function is defined as the flow of a neural ordinary differential equation (neural ODE) at the final time of the integration interval. We …

Learning on Manifolds: Universal Approximations Properties using Geometric Controllability Conditions for Neural ODEs

2023-05-15 · Karthik Elamvazhuthi, Xuechen Zhang, Samet Oymak, Fabio Pasqualetti

In numerous robotics and mechanical engineering applications, among others, data is often constrained on smooth manifolds due to the presence of rotational degrees of freedom. Common datadriven and learning-based methods…

Universal Approximation Constraints of Narrow ResNets: The Tunnel Effect

2026-03-30 · Christian Kuehn, Sara-Viola Kuntz, Tobias Wöhrer arxiv

We analyze the universal approximation constraints of narrow Residual Neural Networks (ResNets) both theoretically and numerically. For deep neural networks without input space augmentation, a central constraint is the i…

Stochastic Modified Flows for Riemannian Stochastic Gradient Descent

2024-02-02 · Benjamin Gess, Sebastian Kassing, Nimit Rana

We give quantitative estimates for the rate of convergence of Riemannian stochastic gradient descent (RSGD) to Riemannian gradient flow and to a diffusion process, the so-called Riemannian stochastic modified flow (RSMF)…

The Broad Consequences of Narrow Banking

2018-10-12

We investigate the macroeconomic consequences of narrow banking in the context of stock-flow consistent models. We begin with an extension of the Goodwin-Keen model incorporating time deposits, government bills, cash, an…