Feature-aligned N-BEATS with Sinkhorn divergence

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Joonhun, Jeon, Myeongho, Kang, Myungjoo, Park, Kyunghyun
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909118934024192
author Lee, Joonhun
Jeon, Myeongho
Kang, Myungjoo
Park, Kyunghyun
author_facet Lee, Joonhun
Jeon, Myeongho
Kang, Myungjoo
Park, Kyunghyun
contents We propose Feature-aligned N-BEATS as a domain-generalized time series forecasting model. It is a nontrivial extension of N-BEATS with doubly residual stacking principle (Oreshkin et al. [45]) into a representation learning framework. In particular, it revolves around marginal feature probability measures induced by the intricate composition of residual and feature extracting operators of N-BEATS in each stack and aligns them stack-wise via an approximate of an optimal transport distance referred to as the Sinkhorn divergence. The training loss consists of an empirical risk minimization from multiple source domains, i.e., forecasting loss, and an alignment loss calculated with the Sinkhorn divergence, which allows the model to learn invariant features stack-wise across multiple source data sequences while retaining N-BEATS's interpretable design and forecasting power. Comprehensive experimental evaluations with ablation studies are provided and the corresponding results demonstrate the proposed model's forecasting and generalization capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2305_15196
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Feature-aligned N-BEATS with Sinkhorn divergence
Lee, Joonhun
Jeon, Myeongho
Kang, Myungjoo
Park, Kyunghyun
Machine Learning
Artificial Intelligence
Optimization and Control
Probability
We propose Feature-aligned N-BEATS as a domain-generalized time series forecasting model. It is a nontrivial extension of N-BEATS with doubly residual stacking principle (Oreshkin et al. [45]) into a representation learning framework. In particular, it revolves around marginal feature probability measures induced by the intricate composition of residual and feature extracting operators of N-BEATS in each stack and aligns them stack-wise via an approximate of an optimal transport distance referred to as the Sinkhorn divergence. The training loss consists of an empirical risk minimization from multiple source domains, i.e., forecasting loss, and an alignment loss calculated with the Sinkhorn divergence, which allows the model to learn invariant features stack-wise across multiple source data sequences while retaining N-BEATS's interpretable design and forecasting power. Comprehensive experimental evaluations with ablation studies are provided and the corresponding results demonstrate the proposed model's forecasting and generalization capabilities.
title Feature-aligned N-BEATS with Sinkhorn divergence
topic Machine Learning
Artificial Intelligence
Optimization and Control
Probability
url https://arxiv.org/abs/2305.15196