Neural Jump Stochastic Differential Equations

Abstract

Many time series are effectively generated by a combination of deterministic continuous flows along with discrete jumps sparked by stochastic events. However, we usually do not have the equation of motion describing the flows, or how they are affected by jumps. To this end, we introduce Neural Jump Stochastic Differential Equations that provide a data-driven approach to learn continuous and discrete dynamic behavior, i.e., hybrid systems that both flow and jump. Our approach extends the framework of Neural Ordinary Differential Equations with a stochastic process term that models discrete events. We then model temporal point processes with a piecewise-continuous latent trajectory, where the discontinuities are caused by stochastic events whose conditional intensity depends on the latent state. We demonstrate the predictive capabilities of our model on a range of synthetic and real-world marked point process datasets, including classical point processes (such as Hawkes processes), awards on Stack Overflow, medical records, and earthquake monitoring.

References in corpus (10)

• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Latent ODEs for Irregularly-Sampled Time Series
• Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems
• DiffEqFlux.jl - A Julia Library for Neural Differential Equations
• Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit
• A Dirichlet Mixture Model of Hawkes Processes for Event Sequence Clustering
• COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution
• Learning Hawkes Processes from Short Doubly-Censored Event Sequences
• Black-box Variational Inference for Stochastic Differential Equations
• A multiscale neural network based on hierarchical matrices

Cited by in corpus (36)

• Neural Controlled Differential Equations for Irregular Time Series
• Scalable Gradients for Stochastic Differential Equations
• Dissecting Neural ODEs
• Learning Long-Term Dependencies in Irregularly-Sampled Time Series
• Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit
• Evolutionary Preference Learning via Graph Nested GRU ODE for Session-based Recommendation
• Optimal control of families of quantum gates
• Learning to Simulate Daily Activities via Modeling Dynamic Human Needs
• Learning Neural Event Functions for Ordinary Differential Equations
• Learning the temporal evolution of multivariate densities via normalizing flows
• Constrained Neural Ordinary Differential Equations with Stability Guarantees
• An end-to-end deep learning approach for extracting stochastic dynamical systems with $\alpha$-stable Lévy noise
• Hypersolvers: Toward Fast Continuous-Depth Models
• STEER: Simple Temporal Regularization For Neural ODEs
• Stochastic Normalizing Flows
• Improving Robustness and Uncertainty Modelling in Neural Ordinary Differential Equations
• Stable Neural Flows
• Learning Multivariate Hawkes Processes at Scale
• Neural Controlled Differential Equations for Online Prediction Tasks
• Stochasticity in Neural ODEs: An Empirical Study
• A General Framework for Survival Analysis and Multi-State Modelling
• Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Models
• Learning dynamics on invariant measures using PDE-constrained optimization
• Learning Continuous-Time Dynamics by Stochastic Differential Networks
• Continuous-Time Model-Based Reinforcement Learning
• An Empirical Study: Extensive Deep Temporal Point Process
• Piecewise-constant Neural ODEs
• Continuous-Depth Neural Models for Dynamic Graph Prediction
• Deep learning and differential equations for modeling changes in individual-level latent dynamics between observation periods
• Efficient and Accurate Gradients for Neural SDEs
• Event Outlier Detection in Continuous Time
• STRODE: Stochastic Boundary Ordinary Differential Equation
• Differentiable Multiple Shooting Layers
• Nonlinear Hawkes Process with Gaussian Process Self Effects
• E2V-SDE: From Asynchronous Events to Fast and Continuous Video Reconstruction via Neural Stochastic Differential Equations
• A Metric Space for Point Process Excitations