Learning to Optimize with Dynamic Mode Decomposition
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F22%3A00360159" target="_blank" >RIV/68407700:21240/22:00360159 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1109/IJCNN55064.2022.9892364" target="_blank" >https://doi.org/10.1109/IJCNN55064.2022.9892364</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/IJCNN55064.2022.9892364" target="_blank" >10.1109/IJCNN55064.2022.9892364</a>
Alternative languages
Result language
angličtina
Original language name
Learning to Optimize with Dynamic Mode Decomposition
Original language description
Designing faster optimization algorithms is of ever-growing interest. In recent years, learning to learn methods that learn how to optimize demonstrated very encouraging results. Current approaches usually do not effectively include the dynamics of the optimization process during training. They either omit it entirely or only implicitly assume the dynamics of an isolated parameter. In this paper, we show how to utilize the dynamic mode decomposition method for extracting informative features about optimization dynamics. By employing those features, we show that our learned optimizer generalizes much better to unseen optimization problems in short. The improved generalization is illustrated on multiple tasks where training the optimizer on one neural network generalizes to different architectures and distinct datasets.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2022 International Joint Conference on Neural Networks (IJCNN)
ISBN
978-1-7281-8671-9
ISSN
—
e-ISSN
2161-4407
Number of pages
8
Pages from-to
1-8
Publisher name
IEEE Industrial Electronic Society
Place of publication
Vienna
Event location
Padua
Event date
Jul 18, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000867070903123