An Introduction to Stochastic Deep Learning
- 1Department of Statistics, Purdue University, West Lafayette, Indiana, USA.
Abstract
Deep neural networks (DNNs) have achieved remarkable success in prediction, but their deterministic formulation makes many statistical inference tasks difficult. StoNet, short for stochastic neural network, addresses this limitation by reformulating a DNN as a probabilistic latent-variable model, in which the outputs of selected hidden layers or units are treated as latent variables. The article describes the formulation of StoNet and its asymptotic equivalence to a conventional DNN, showing how StoNet can serve both as a deep learning model and as an analytical device for studying DNNs. It reviews training algorithms for StoNet and discusses its applications to statistical inference problems, including nonlinear sufficient dimension reduction, causal inference with observed and unobserved confounders, Granger-causality learning for nonlinear time series, nonlinear variable selection, and prediction uncertainty quantification for large-scale DNNs. The article also discusses two related architectures: kernel-expanded StoNet and sublinearly structured DNNs, which can be viewed as structural or theoretical extensions of the StoNet framework. Under suitable architectural conditions, the former is immune to local traps in training and tends to outperform conventional DNNs in prediction; whereas the latter achieves feature-learning consistency in over-parameterized regimes when the training sample size is sufficiently large. Together, these developments show that StoNet broadens deep learning from prediction-oriented function approximation to a richer framework for statistical inference.
Related
- Deep Neural Operator Learning for stochastic heat equations and applications
- Deep operator learning for efficient sampling from invariant measures of stochastic differential equations
- Deep learning methods for stochastic Galerkin approximations of random domain problems
- Deep Pontryagin Learning for Continuous-Time Stochastic Control with Jumps
- Spread of Chronic Wasting Disease under Stochastic Environmental Conditions and its Control using Deep Reinforcement Learning
BibTeX
@article{liang2026introduction,
title = {{An Introduction to Stochastic Deep Learning}},
author = {Faming Liang},
journal = {Wiley interdisciplinary reviews. Computational statistics},
year = {2026},
month = sep,
doi = {10.1002/wics.70076},
url = {https://europepmc.org/article/PMC/PMC13717249},
note = {CC BY},
}
RIS
TY - JOUR
TI - An Introduction to Stochastic Deep Learning
AU - Faming Liang
PY - 2026
DA - 2026/09/01
JO - Wiley interdisciplinary reviews. Computational statistics
DO - 10.1002/wics.70076
UR - https://europepmc.org/article/PMC/PMC13717249
AB - Deep neural networks (DNNs) have achieved remarkable success in prediction, but their deterministic formulation makes many statistical inference tasks difficult. StoNet, short for stochastic neural network, addresses this limitation by reformulating a DNN as a probabilistic latent-variable model, in which the outputs of selected hidden layers or units are treated as latent variables. The article describes the formulation of StoNet and its asymptotic equivalence to a conventional DNN, showing how StoNet can serve both as a deep learning model and as an analytical device for studying DNNs. It reviews training algorithms for StoNet and discusses its applications to statistical inference problems, including nonlinear sufficient dimension reduction, causal inference with observed and unobserved confounders, Granger-causality learning for nonlinear time series, nonlinear variable selection, and prediction uncertainty quantification for large-scale DNNs. The article also discusses two related architectures: kernel-expanded StoNet and sublinearly structured DNNs, which can be viewed as structural or theoretical extensions of the StoNet framework. Under suitable architectural conditions, the former is immune to local traps in training and tends to outperform conventional DNNs in prediction; whereas the latter achieves feature-learning consistency in over-parameterized regimes when the training sample size is sufficiently large. Together, these developments show that StoNet broadens deep learning from prediction-oriented function approximation to a richer framework for statistical inference.
SN - 1939-5108
SN - 1939-0068
ER -