Theoretical Guarantees for Learning Conditional Expectation using Controlled ODE-RNN

06/08/2020
by   Calypso Herrera, et al.
0

Continuous stochastic processes are widely used to model time series that exhibit a random behaviour. Predictions of the stochastic process can be computed by the conditional expectation given the current information. To this end, we introduce the controlled ODE-RNN that provides a data-driven approach to learn the conditional expectation of a stochastic process. Our approach extends the ODE-RNN framework which models the latent state of a recurrent neural network (RNN) between two observations with a neural ordinary differential equation (neural ODE). We show that controlled ODEs provide a general framework which can in particular describe the ODE-RNN, combining in a single equation the continuous neural ODE part with the jumps introduced by RNN. We demonstrate the predictive capabilities of this model by proving that, under some regularities assumptions, the output process converges to the conditional expectation process.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/02/2021

Framing RNN as a kernel method: A neural ODE approach

Building on the interpretation of a recurrent neural network (RNN) as a ...
research
05/24/2019

Neural Jump Stochastic Differential Equations

Many time series can be effectively modeled with a combination of contin...
research
06/02/2023

Neural Differential Recurrent Neural Network with Adaptive Time Steps

The neural Ordinary Differential Equation (ODE) model has shown success ...
research
08/23/2023

Neural oscillators for magnetic hysteresis modeling

Hysteresis is a ubiquitous phenomenon in science and engineering; its mo...
research
08/22/2019

Learning stochastic differential equations using RNN with log signature features

This paper contributes to the challenge of learning a function on stream...
research
07/11/2023

Enhancing Continuous Time Series Modelling with a Latent ODE-LSTM Approach

Due to their dynamic properties such as irregular sampling rate and high...
research
03/28/2022

Neural Estimation and Optimization of Directed Information over Continuous Spaces

This work develops a new method for estimating and optimizing the direct...

Please sign up or login with your details

Forgot password? Click here to reset