Implicit Reasoning in Deep Time Series Forecasting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Potosnak, Willa, Challu, Cristian, Goswami, Mononito, Wiliński, Michał, Żukowska, Nina, Dubrawski, Artur
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916475398258688
author Potosnak, Willa
Challu, Cristian
Goswami, Mononito
Wiliński, Michał
Żukowska, Nina
Dubrawski, Artur
author_facet Potosnak, Willa
Challu, Cristian
Goswami, Mononito
Wiliński, Michał
Żukowska, Nina
Dubrawski, Artur
contents Recently, time series foundation models have shown promising zero-shot forecasting performance on time series from a wide range of domains. However, it remains unclear whether their success stems from a true understanding of temporal dynamics or simply from memorizing the training data. While implicit reasoning in language models has been studied, similar evaluations for time series models have been largely unexplored. This work takes an initial step toward assessing the reasoning abilities of deep time series forecasting models. We find that certain linear, MLP-based, and patch-based Transformer models generalize effectively in systematically orchestrated out-of-distribution scenarios, suggesting underexplored reasoning capabilities beyond simple pattern memorization.
format Preprint
id arxiv_https___arxiv_org_abs_2409_10840
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Implicit Reasoning in Deep Time Series Forecasting
Potosnak, Willa
Challu, Cristian
Goswami, Mononito
Wiliński, Michał
Żukowska, Nina
Dubrawski, Artur
Machine Learning
Recently, time series foundation models have shown promising zero-shot forecasting performance on time series from a wide range of domains. However, it remains unclear whether their success stems from a true understanding of temporal dynamics or simply from memorizing the training data. While implicit reasoning in language models has been studied, similar evaluations for time series models have been largely unexplored. This work takes an initial step toward assessing the reasoning abilities of deep time series forecasting models. We find that certain linear, MLP-based, and patch-based Transformer models generalize effectively in systematically orchestrated out-of-distribution scenarios, suggesting underexplored reasoning capabilities beyond simple pattern memorization.
title Implicit Reasoning in Deep Time Series Forecasting
topic Machine Learning
url https://arxiv.org/abs/2409.10840