top of page

 > 最新消息 > 學術活動 > Distributed Adaptive Gradient Methods for Online Optimization

【學術活動】Distributed Adaptive Gradient Methods for Online Optimization

日曆.png

2023-10-03

夾.png

112年10月11日(星期三)舉辦專題演講,

歡迎大家踴躍參加,相關資訊如下。

演講題目:Distributed Adaptive Gradient Methods for Online Optimization

 

演講講者:Professor George Michailidis   (   Department of Statistics and Data Science   University of California, Los Angeles (UCLA)   )

 

演講時間:2023/10/11 (三) 14:20-16:00

 

演講地點:臺灣大學國青大樓101會議室

 

Abstract:

Adaptive gradient based optimization methods (Adam, Adagrad, RMSProp) are widely used in solving large scale machine learning problems including training deep learning neural networks. A number of schemes have been proposed in the literature aiming at parallelizing them, based on communications of peripheral nodes with a central node, or amongst themselves. In this presentation, we briefly review centralized adaptive gradient based algorithms and then introduce and discuss their distributed variants. We present their convergence properties in both stochastic and deterministic settings. The algorithms are illustrated on applications, including training of deep neural networks.

presentation 20231011-1.jpg

聯 繋

專員:魏婉鈞小姐

統編:01053665

信箱:service@ciie.org.tw

電話:02-2959-8503(週一 ~ 五 9 am ~ 6 pm)

傳真:02-2959-8503(請先來電告知再撥號碼,響10聲後自動轉傳真)

地址:22063新北市板橋區中山路一段1號20樓之14

【主編信箱】

曾明朗教授:jipe@asia.edu.tw

曹譽鐘教授:jipe@mail.ntust.edu.tw

Copyright © 社團法人中國工業工程學會

Chinese Institute of Industrial Engineers (CIIE)

bottom of page