Exploring variance reduction in importance sampling for efficient DNN training

DOI10.1137/25M1726339MaRDI QIDQ6876748zbMATH OpenFDO

Authors Takuro Kutsuna

Publication date 12 January 2026

Published in SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1137/25M1726339

zbMATH Keywords

deep neural networkimportance samplingvariance reduction

Mathematics Subject Classification ID

Sampling theory, sample surveys (62D05) Artificial neural networks and deep learning (68T07)

Cites work

• A theoretical framework for sequential importance sampling with resampling.

This page was built for publication: Exploring variance reduction in importance sampling for efficient DNN training

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6876748)