Saved in:
Bibliographic Details
Main Authors: Yu, Chenxu, Fang, Wenqi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.25024
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917362417008640
author Yu, Chenxu
Fang, Wenqi
author_facet Yu, Chenxu
Fang, Wenqi
contents As a representative continuous-depth neural network approach, stochastic differential equation (SDE)-based Bayesian neural networks (BNNs) have attracted considerable attention due to their solid theoretical foundations and strong potential for real-world applications. However, their reliance on numerical SDE solvers inevitably incurs a large number of function evaluations (NFEs), resulting in high computational cost and occasional convergence instability. To address these challenges, we propose a Nesterov-accelerated gradient (NAG) enhanced SDE-BNN model. By integrating NAG into the SDE-BNN framework along with an NFE-dependent residual skip connection, our method accelerates convergence and substantially reduces NFEs during both training and testing. Extensive empirical results show that our model consistently outperforms conventional SDE-BNNs across various tasks, including image classification and sequence modeling, achieving lower NFEs and improved predictive accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2603_25024
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Improving Infinitely Deep Bayesian Neural Networks with Nesterov's Accelerated Gradient Method
Yu, Chenxu
Fang, Wenqi
Machine Learning
As a representative continuous-depth neural network approach, stochastic differential equation (SDE)-based Bayesian neural networks (BNNs) have attracted considerable attention due to their solid theoretical foundations and strong potential for real-world applications. However, their reliance on numerical SDE solvers inevitably incurs a large number of function evaluations (NFEs), resulting in high computational cost and occasional convergence instability. To address these challenges, we propose a Nesterov-accelerated gradient (NAG) enhanced SDE-BNN model. By integrating NAG into the SDE-BNN framework along with an NFE-dependent residual skip connection, our method accelerates convergence and substantially reduces NFEs during both training and testing. Extensive empirical results show that our model consistently outperforms conventional SDE-BNNs across various tasks, including image classification and sequence modeling, achieving lower NFEs and improved predictive accuracy.
title Improving Infinitely Deep Bayesian Neural Networks with Nesterov's Accelerated Gradient Method
topic Machine Learning
url https://arxiv.org/abs/2603.25024