Saved in:
Bibliographic Details
Main Authors: Nivron, Omer, Parthipan, Raghul, Wischik, Damon J.
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2305.19141
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917782396862464
author Nivron, Omer
Parthipan, Raghul
Wischik, Damon J.
author_facet Nivron, Omer
Parthipan, Raghul
Wischik, Damon J.
contents We propose the Taylorformer for random processes such as time series. Its two key components are: 1) the LocalTaylor wrapper which adapts Taylor approximations (used in dynamical systems) for use in neural network-based probabilistic models, and 2) the MHA-X attention block which makes predictions in a way inspired by how Gaussian Processes' mean predictions are linear smoothings of contextual data. Taylorformer outperforms the state-of-the-art in terms of log-likelihood on 5/6 classic Neural Process tasks such as meta-learning 1D functions, and has at least a 14\% MSE improvement on forecasting tasks, including electricity, oil temperatures and exchange rates. Taylorformer approximates a consistent stochastic process and provides uncertainty-aware predictions. Our code is provided in the supplementary material.
format Preprint
id arxiv_https___arxiv_org_abs_2305_19141
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Taylorformer: Probabilistic Modelling for Random Processes including Time Series
Nivron, Omer
Parthipan, Raghul
Wischik, Damon J.
Machine Learning
We propose the Taylorformer for random processes such as time series. Its two key components are: 1) the LocalTaylor wrapper which adapts Taylor approximations (used in dynamical systems) for use in neural network-based probabilistic models, and 2) the MHA-X attention block which makes predictions in a way inspired by how Gaussian Processes' mean predictions are linear smoothings of contextual data. Taylorformer outperforms the state-of-the-art in terms of log-likelihood on 5/6 classic Neural Process tasks such as meta-learning 1D functions, and has at least a 14\% MSE improvement on forecasting tasks, including electricity, oil temperatures and exchange rates. Taylorformer approximates a consistent stochastic process and provides uncertainty-aware predictions. Our code is provided in the supplementary material.
title Taylorformer: Probabilistic Modelling for Random Processes including Time Series
topic Machine Learning
url https://arxiv.org/abs/2305.19141