Investigation into Training Dynamics of Learned Optimizers (Student Abstract)
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F24%3A00375860" target="_blank" >RIV/68407700:21240/24:00375860 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1609/aaai.v38i21.30514" target="_blank" >https://doi.org/10.1609/aaai.v38i21.30514</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1609/aaai.v38i21.30514" target="_blank" >10.1609/aaai.v38i21.30514</a>
Alternative languages
Result language
angličtina
Original language name
Investigation into Training Dynamics of Learned Optimizers (Student Abstract)
Original language description
Modern machine learning heavily relies on optimization, and as deep learning models grow more complex and data-hungry, the search for efficient learning becomes crucial. Learned optimizers disrupt traditional handcrafted methods such as SGD and Adam by learning the optimization strategy itself, potentially speeding up training. However, the learned optimizers' dynamics are still not well understood. To remedy this, our work explores their optimization trajectories from the perspective of network architecture symmetries and proposed parameter update distributions.
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
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 38th AAAI Conference on Artificial Intelligence
ISBN
978-1-57735-887-9
ISSN
2159-5399
e-ISSN
2374-3468
Number of pages
2
Pages from-to
23657-23658
Publisher name
AAAI Press
Place of publication
Menlo Park
Event location
Vancouver
Event date
Feb 20, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001239989100210