Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Schedule-free optimization of the transformers-based time series forecasting model

IAES International Journal of Artificial Intelligence · Vol. 14 No. 2 (2025) · hlm. 1067–1076

DOI
10.11591/ijai.v14.i2.pp1067-1076
ISSN
2252-8938, 2089-4872
Terbit
2025-04-01
Penerbit
Institute of Advanced Engineering and Science
Bahasa
eng
Lisensi
creativecommons.org/licenses/by-sa/4.0

Abstrak

The task of time series forecasting is important for many scientific, technical, and applied fields, such as finance, economics, meteorology, medicine, transportation, and telecommunications. Existing methods, such as autoregressive models and moving average models, have their limitations, especially when working with non-stationary and seasonal data. In this work, the basic architecture of transformers was modified to solve time series forecasting problems. Additionally, state-of-the-art optimizers were investigated and experimentally compared, including AdamW, stochastic gradient descent (SGD), and new methods such as schedule-free SGD and schedule-free AdamW, to improve forecasting accuracy and the efficiency of the training procedure for the transformer architecture. Modeling was conducted on meteorological data that included seasonal time series. The accuracy evaluation of the optimization methods studied in this work was performed using a range of different performance indicators. The results showed that the new optimization methods significantly improve forecasting accuracy compared to the use of traditional optimizers.

Kata kunci

Jaringan kolaborasi para penulis

8 penulis · 24 tautan kepenulisan bersama · 11 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Lviv Polytechnic National University
  • Comenius University Bratislava
  • University of Birmingham
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Ivan IzoninLviv Polytechnic National University3
Roman MuzykaLviv Polytechnic National University3
Roman TkachenkoLviv Polytechnic National University3
Roman KorzhLviv Polytechnic National University2
Natalya KustraLviv Polytechnic National University1
Stergios-Aristoteles MitoulisUniversity of Birmingham1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) http://ijai.iaescore.com/index.php/IJAI/oai, pertama di-harvest 8 Nov 2026, terakhir terlihat 16 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Schedule-free optimization of the transformers-based time series forecasting model</dc:title>
	<dc:creator>Yemets, Kyrylo</dc:creator>
	<dc:creator>Greguš, Michal</dc:creator>
	<dc:subject xml:lang="en-US">Neural Network;</dc:subject>
	<dc:subject xml:lang="en-US">AdaGrad; Forecasting; RMSprop; Schedule-Free AdamW; Schedule-Free SGD; Time series; Transformers;</dc:subject>
	<dc:description xml:lang="en-US">The task of time series forecasting is important for many scientific, technical, and applied fields, such as finance, economics, meteorology, medicine, transportation, and telecommunications. Existing methods, such as autoregressive models and moving average models, have their limitations, especially when working with non-stationary and seasonal data. In this work, the basic architecture of transformers was modified to solve time series forecasting problems. Additionally, state-of-the-art optimizers were investigated and experimentally compared, including AdamW, stochastic gradient descent (SGD), and new methods such as schedule-free SGD and schedule-free AdamW, to improve forecasting accuracy and the efficiency of the training procedure for the transformer architecture. Modeling was conducted on meteorological data that included seasonal time series. The accuracy evaluation of the optimization methods studied in this work was performed using a range of different performance indicators. The results showed that the new optimization methods significantly improve forecasting accuracy compared to the use of traditional optimizers.</dc:description>
	<dc:publisher xml:lang="en-US">Institute of Advanced Engineering and Science</dc:publisher>
	<dc:contributor xml:lang="en-US">Horizon Europe</dc:contributor>
	<dc:date>2025-04-01</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US"></dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://ijai.iaescore.com/index.php/IJAI/article/view/26616</dc:identifier>
	<dc:identifier>10.11591/ijai.v14.i2.pp1067-1076</dc:identifier>
	<dc:source xml:lang="en-US">IAES International Journal of Artificial Intelligence (IJ-AI); Vol 14, No 2: April 2025; 1067-1076</dc:source>
	<dc:source>2252-8938</dc:source>
	<dc:source>2089-4872</dc:source>
	<dc:source>10.11591/ijai.v14.i2</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://ijai.iaescore.com/index.php/IJAI/article/view/26616/14433</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2025 Institute of Advanced Engineering and Science</dc:rights>
	<dc:rights xml:lang="en-US">http://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>