Recurrent Interpolants for Probabilistic Time Series Prediction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Yu, Biloš, Marin, Mittal, Sarthak, Deng, Wei, Rasul, Kashif, Schneider, Anderson
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929527622467584
author Chen, Yu
Biloš, Marin
Mittal, Sarthak
Deng, Wei
Rasul, Kashif
Schneider, Anderson
author_facet Chen, Yu
Biloš, Marin
Mittal, Sarthak
Deng, Wei
Rasul, Kashif
Schneider, Anderson
contents Sequential models like recurrent neural networks and transformers have become standard for probabilistic multivariate time series forecasting across various domains. Despite their strengths, they struggle with capturing high-dimensional distributions and cross-feature dependencies. Recent work explores generative approaches using diffusion or flow-based models, extending to time series imputation and forecasting. However, scalability remains a challenge. This work proposes a novel method combining recurrent neural networks' efficiency with diffusion models' probabilistic modeling, based on stochastic interpolants and conditional generation with control features, offering insights for future developments in this dynamic field.
format Preprint
id arxiv_https___arxiv_org_abs_2409_11684
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Recurrent Interpolants for Probabilistic Time Series Prediction
Chen, Yu
Biloš, Marin
Mittal, Sarthak
Deng, Wei
Rasul, Kashif
Schneider, Anderson
Machine Learning
Sequential models like recurrent neural networks and transformers have become standard for probabilistic multivariate time series forecasting across various domains. Despite their strengths, they struggle with capturing high-dimensional distributions and cross-feature dependencies. Recent work explores generative approaches using diffusion or flow-based models, extending to time series imputation and forecasting. However, scalability remains a challenge. This work proposes a novel method combining recurrent neural networks' efficiency with diffusion models' probabilistic modeling, based on stochastic interpolants and conditional generation with control features, offering insights for future developments in this dynamic field.
title Recurrent Interpolants for Probabilistic Time Series Prediction
topic Machine Learning
url https://arxiv.org/abs/2409.11684