SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates

Abstract

Uncertainty quantification is a fundamental yet unsolved problem for deep learning. The Bayesian framework provides a principled way of uncertainty estimation but is often not scalable to modern deep neural nets (DNNs) that have a large number of parameters. Non-Bayesian methods are simple to implement but often conflate different sources of uncertainties and require huge computing resources. We propose a new method for quantifying uncertainties of DNNs from a dynamical system perspective. The core of our method is to view DNN transformations as state evolution of a stochastic dynamical system and introduce a Brownian motion term for capturing epistemic uncertainty. Based on this perspective, we propose a neural stochastic differential equation model (SDE-Net) which consists of (1) a drift net that controls the system to fit the predictive function; and (2) a diffusion net that captures epistemic uncertainty. We theoretically analyze the existence and uniqueness of the solution to SDE-Net. Our experiments demonstrate that the SDE-Net model can outperform existing uncertainty estimation methods across a series of tasks where uncertainty plays a fundamental role.

arXiv commentICML2020. Code is available through https://github.com/Lingkai-Kong/SDE-Net

Cited by in corpus (12)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty
• STUaNet: Understanding uncertainty in spatiotemporal collective human mobility
• DS-UI: Dual-Supervised Mixture of Gaussian Mixture Models for Uncertainty Inference
• Climate Modeling with Neural Diffusion Equations
• When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting
• Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression
• Efficient and Accurate Gradients for Neural SDEs
• Accurate and Reliable Forecasting using Stochastic Differential Equations
• Collaborative Uncertainty in Multi-Agent Trajectory Forecasting
• E2V-SDE: From Asynchronous Events to Fast and Continuous Video Reconstruction via Neural Stochastic Differential Equations
• Dense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Model