Work

A Generalization Bound of Deep Neural Networks for Dependent Data

Year: 2023

Type: preprint

Abstract: Existing generalization bounds for deep neural networks require data to be independent and identically distributed (iid). This assumption may not hold in real-life applications such as evolutionary biology, infectious disease epidemiology, and stock price prediction. This work establishes a generalization bound of feed-forward neural networks for non-stationary $ϕ$-mixing data.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2310.05892

Authors: Do, Quan Huu, Nguyen, Binh T., Ho, Lam Si Tung

Institutions: Vietnam National University Ho Chi Minh City, Ho Chi Minh City University of Science

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Canada Research Chairs, Natural Sciences and Engineering Research Council of Canada

Awards: G1677900737, G6492271423, Advancing statistical inference for correlated and partially observed data, G814497173

OpenAlex ID: W4387560512

Cites:

Cited by: 3

Related to: 10