paper-with-me

홈 › Papers

Forward and Inverse Approximation Theory for Linear Temporal Convolutional Networks

2023-05-29 · Haotian Jiang, Qianxiao Li

We present a theoretical analysis of the approximation properties of convolutional architectures when applied to the modeling of temporal sequences. Specifically, we prove an approximation rate estimate (Jackson-type result) and an inverse approximation theorem (Bernstein-type result), which together provide a comprehensive characterization of the types of sequential relationships that can be efficiently captured by a temporal convolutional architecture. The rate estimate improves upon a previous result via the introduction of a refined complexity measure, whereas the inverse approximation theorem is new.

📄 PDF Abstract BibTeX arXiv:2305.18478

Code (0)

등록된 구현이 없습니다.

Tasks

Temporal Sequences

Similar Papers 제목 키워드 기반

Fredholm Neural Networks for forward and inverse problems in elliptic PDEs

2025-07-08 · Kyriakos Georgiou, Constantinos Siettos, Athanasios N. Yannacopoulos

Building on our previous work introducing Fredholm Neural Networks (Fredholm NNs/ FNNs) for solving integral equations, we extend the framework to tackle forward and inverse problems for linear and semi-linear elliptic p…

Inverse Approximation Theory for Nonlinear Recurrent Neural Networks

2023-05-30 · Shida Wang, Zhong Li, Qianxiao Li

We prove an inverse approximation theorem for the approximation of nonlinear sequence-to-sequence relationships using recurrent neural networks (RNNs). This is a so-called Bernstein-type result in approximation theory, w…

Learning Partial Differential Equations by Spectral Approximates of General Sobolev Spaces

2023-01-12 · Juan-Esteban Suarez Cardona, Phil-Alexander Hofmann, Michael Hecht

We introduce a novel spectral, finite-dimensional approximation of general Sobolev spaces in terms of Chebyshev polynomials. Based on this polynomial surrogate model (PSM), we realise a variational formulation, solving a…

Inverse Extended Kalman Filter -- Part II: Highly Non-Linear and Uncertain Systems

2022-08-13 · Himali Singh, Arpan Chattopadhyay, Kumar Vijay Mishra

Counter-adversarial system design problems have lately motivated the development of inverse Bayesian filters. For example, inverse Kalman filter (I-KF) has been recently formulated to estimate the adversary's Kalman-filt…

State Estimation

Novel Deep neural networks for solving Bayesian statistical inverse

2021-02-08 · Harbir Antil, Howard C Elman, Akwum Onwunta, Deepanshu Verma

We consider the simulation of Bayesian statistical inverse problems governed by large-scale linear and nonlinear partial differential equations (PDEs). Markov chain Monte Carlo (MCMC) algorithms are standard techniques t…