[Turkmath:6830] Galatasaray Üniversitesi Seminer Duyurusu - Ozgur Martin - 04.12.24

[Galatasaray Üniversitesi Matematik Seminerleri]

Speaker:  Özgür Martin - Mimar Sinan Güzel Sanatlar Üniversitesi
Date: 04.12.2024
Time: 15:00 - 16:00
Location: Galatasaray Üniversitesi, Ortaköy, Çırağan Cd. No:36, 34349 
Beşiktaş, H 306


*Title*: How to train your large AI model at a lower cost?

*Abstract*: Stochastic gradient descent (SGD) method and its variants 
constitute the core optimization algorithms that are used for training 
large-scale machine learning models. These algorithms achieve very good 
convergence rates, especially when they are fine-tuned for the 
application at hand. Unfortunately, this tuning process can require 
large computational costs. For example, GPT-4 (the core machinery of 
ChatGPT), was trained using trillions of words of text and many 
thousands of powerful computer chips. The electric bill for the training 
was over $100 million [1].

Recent work has shown that these costs can be reduced by choosing the 
learning rate adaptively. We propose an alternative approach to this 
problem by using a new algorithm based on forward step model building 
[2] built upon SGD.

[1] 
https://www.wired.com/story/openai-ceo-sam-altman-the-age-of-giant-ai-models-is-already-over/ 
<https://www.google.com/url?q=https://www.wired.com/story/openai-ceo-sam-altman-the-age-of-giant-ai-models-is-already-over/&sa=D&source=calendar&ust=1733510532993228&usg=AOvVaw2WtDjtx0KyPQTkx9AwnHX9> 


[2] Birbil, Ş.İ., Martin, Ö., Onay, G., Öztoprak, F., Bolstering 
stochastic gradient descent with model building. TOP 32, 517–536 (2024). 
https://doi.org/10.1007/s11750-024-00673-z 
<https://www.google.com/url?q=https://doi.org/10.1007/s11750-024-00673-z&sa=D&source=calendar&ust=1733510532993228&usg=AOvVaw0gYAxvawzcpt5CzeozXV3D>


* To access to the complete seminar calendar please visit this link

https://matematik.gsu.edu.tr/tr/arastirma/seminerler

* To add to your calendar use ical url.

https://calendar.google.com/calendar/ical/mathseminar%40galatasaray.education/public/basic.ics

* Participants from outside Galatasaray Üniversitesi are kindly
requested to send an email to mathseminar at galatasaray.education
before 13:00 on the day of the seminar.

---
Galatasaray Üniversitesi Matematik Bölümü


https://matematik.gsu.edu.tr/







-------------- sonraki b�l�m --------------
Bir HTML eklentisi temizlendi...
URL: <http://yunus.listweb.bilkent.edu.tr/pipermail/turkmath/attachments/20241202/503aaed6/attachment.html>