Skip navigation

Main Menu

Global Menu

Activities

Search

Seminars

Seminars

seminar view

Seminar View

Seminar
FIELD AI and Natural Sciences
DATE September 01 (Wed), 2021
TIME 14:00-16:00
PLACE 7323
SPEAKER 한정훈
HOST Hyeon, Changbong
INSTITUTE 성균관대학교
TITLE Fluctuation-dissipation Type Theorem in Stochastic Linear Learning
ABSTRACT

The fluctuation-dissipation theorem (FDT) is a simple yet powerful consequence of the first-order differential equation governing the dynamics of systems subject simultaneously to dissipative and stochastic forces. The linear learning dynamics, in which the input vector maps to the output vector by a linear matrix whose elements are the subject of learning, has a stochastic version closely mimicking the Langevin dynamics when a full-batch gradient descent scheme is replaced by that of stochastic gradient descent. We derive a generalized FDT for the stochastic linear learning dynamics and verify its validity among the well-known machine learning data sets such as MNIST, CIFAR-10 and EMNIST.

FILE  
  • list

Seminar List

 

Subject

keyword

date

~