Traversing Time with Multi-Resolution Gaussian Process State-Space Models

by   Krista Longi, et al.

Gaussian Process state-space models capture complex temporal dependencies in a principled manner by placing a Gaussian Process prior on the transition function. These models have a natural interpretation as discretized stochastic differential equations, but inference for long sequences with fast and slow transitions is difficult. Fast transitions need tight discretizations whereas slow transitions require backpropagating the gradients over long subtrajectories. We propose a novel Gaussian process state-space architecture composed of multiple components, each trained on a different resolution, to model effects on different timescales. The combined model allows traversing time on adaptive scales, providing efficient inference for arbitrarily long sequences with complex dynamics. We benchmark our novel method on semi-synthetic data and on an engine modeling task. In both experiments, our approach compares favorably against its state-of-the-art alternatives that operate on a single time-scale only.



There are no comments yet.


page 1

page 2

page 3

page 4


Safe Policy Search with Gaussian Process Models

We propose a method to optimise the parameters of a policy which will be...

Deep State-Space Gaussian Processes

This paper is concerned with a state-space approach to deep Gaussian pro...

Fast Variational Learning in State-Space Gaussian Process Models

Gaussian process (GP) regression with 1D inputs can often be performed i...

Structured Variational Inference in Unstable Gaussian Process State Space Models

Gaussian processes are expressive, non-parametric statistical models tha...

Computationally Efficient Bayesian Learning of Gaussian Process State Space Models

Gaussian processes allow for flexible specification of prior assumptions...

A Gaussian process latent force model for joint input-state estimation in linear structural systems

The problem of combined state and input estimation of linear structural ...

Controlled Gaussian Process Dynamical Models with Application to Robotic Cloth Manipulation

Over the last years, robotic cloth manipulation has gained relevance wit...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.