February 23, 2022 18:20

Abstract

The TrustML Young Scientist Seminars (TrustML YSS) started from January 28, 2022.

The TrustML YSS is a video series that features young scientists giving talks and discoveries in relation with Trustworthy Machine Learning.

For more information please see the following site.
TrustML YSS

This network is funded by RIKEN-AIP’s subsidy and JST, ACT-X Grant Number JPMJAX21AF, Japan.


【The 6th Seminar】


Date and Time: March 10th 5:15pm – 6:15pm(JST)

Venue: Zoom webinar

Language: English


Speaker: Kfir Y. Levy (Technion)
Title: Beyond SGD: Efficient Learning with Non i.i.d. Data
Abstract:
The tremendous success of the Machine Learning paradigm heavily relies on the development of powerful optimization methods. The canonical algorithm for training learning models is SGD (Stochastic Gradient Descent), yet this method has several limitations. In particular, it relies on the assumption that data-points are i.i.d. (independent and identically distributed); however this assumption does not necessarily hold in practice.

In this talk, I will discuss an ongoing line of research where we develop alternative methods that resolve this limitation of SGD in two different contexts. In the first part of the talk, I will describe a method that enables to cope well with contaminated data. In the second part, I will discuss a method that enables an efficient handling of Markovian data. The methods that I describe are as efficient as SGD, and implicitly adapt to the underlying structure of the problem in a data dependent manner.


All participants are required to agree with the AIP Seminar Series Code of Conduct.
Please see the URL below.
https://aip.riken.jp/event-list/termsofparticipation/?lang=en

RIKEN AIP will expect adherence to this code throughout the event. We expect cooperation from all participants to help ensure a safe environment for everybody.


More Information

Date March 10, 2022 (Thu) 17:15 - 18:15
URL https://c5dc59ed978213830355fc8978.doorkeeper.jp/events/133772

Related Laboratories

last updated on November 27, 2024 10:28Laboratory