Neural Stochastic Differential Equations on Compact State Spaces: Theory, Methods, and Application to Suicide Risk Modeling
stat.ML, cs.LG
Submitted: 2025-08-23
Updated: 2026-09-15
Comments: Accepted at The 1st Symposium on Probabilistic Machine Learning (ProbML) 2026, and at the Methods and Opportunities at Small Scale (MOSS), ICML 2025, Vancouver, Canada
Code: https://github.com/mogu-lab/wsp-demo
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Continuously Differentiable Exponential Linear Units
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- Validating Stochastic Models: Invariance Criteria for Systems of Stochastic Differential Equations and the Selection of a Stochastic Hodgkin-Huxley Type Model
- Gaussian Error Linear Units (GELUs)
- Adam: A Method for Stochastic Optimization
- Spectral Normalization for Generative Adversarial Networks
- Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro
- Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding
- Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
- Online Conformal Prediction for Non-Exchangeable Panel Data
- Deep Time-Series Forecasting in 10 Years: A Survey