paper-with-me

Papers

Deep Learning via Dynamical Systems: An Approximation Perspective

2019-12-22 · Qianxiao Li, Ting Lin, Zuowei Shen

We build on the dynamical systems approach to deep learning, where deep residual networks are idealized as continuous-time dynamical systems, from the approximation perspective. In particular, we establish general sufficient conditions for universal approximation using continuous-time deep residual networks, which can also be understood as approximation theories in $L^p$ using flow maps of dynamical systems. In specific cases, rates of approximation in terms of the time horizon are also established. Overall, these results reveal that composition function approximation through flow maps present a new paradigm in approximation theory and contributes to building a useful mathematical framework to investigate deep learning.

📄 PDF Abstract BibTeX arXiv:1912.10382

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learning

Similar Papers 제목 키워드 기반

An Information Criterion for Inferring Coupling in Distributed Dynamical Systems

2016-05-23 · Oliver M. Cliff, Mikhail Prokopenko, Robert Fitch

The behaviour of many real-world phenomena can be modelled by nonlinear dynamical systems whereby a latent system state is observed through a filter. We are interested in interacting subsystems of this form, which we mod…

On the Universal Approximation Property of Deep Fully Convolutional Neural Networks

2022-11-25 · Ting Lin, Zuowei Shen, Qianxiao Li

We study the approximation of shift-invariant or equivariant functions by deep fully convolutional networks from the dynamical systems perspective. We prove that deep residual fully convolutional networks and their conti…

Koopman Operator Dynamical Models: Learning, Analysis and Control

2021-02-04 · Petar Bevanda, Stefan Sosnowski, Sandra Hirche

The Koopman operator allows for handling nonlinear systems through a (globally) linear representation. In general, the operator is infinite-dimensional - necessitating finite approximations - for which there is no overar…

Quantizing Time-Series Models As Dynamical Systems: Trajectory-Based Quantization Sensitivity Score

2026-06-11 · Mariya Pavlova, Harrison Bo Hua Zhu, Lidia Vitanova, Elizaveta Semenova 외 arxiv

We introduce the Trajectory-based Quantization Sensitivity Score (TQS), a metric that reframes post-training quantization (PTQ) through the lens of dynamical-systems stability. By modeling the network's rollout as a disc…

Flowing Through Layers: A Continuous Dynamical Systems Perspective on Transformers

2025-02-08 · Jacob Fein-Ashley

We show that the standard discrete update rule of transformer layers can be naturally interpreted as a forward Euler discretization of a continuous dynamical system. Our Transformer Flow Approximation Theorem demonstrate…