BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//University of Utah Math Department//Preconditioning for Accelerated Gradient Descent Optimization and Regularization//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Preconditioning for Accelerated Gradient Descent Optimization and Regularization
X-WR-CALDESC:Preconditioning for Accelerated Gradient Descent Optimization and Regularization at University of Utah Mathematics Department
X-WR-TIMEZONE:America/Denver
BEGIN:VEVENT
UID:20241017T160000-qiang-ye@math.utah.edu
DTSTART;TZID=America/Denver:20241017T160000
DTEND;TZID=America/Denver:20241017T170000
DTSTAMP:20260922T150857Z
SUMMARY:Preconditioning for Accelerated Gradient Descent Optimization and Regularization
DESCRIPTION:Speaker: Qiang Ye\, University of Kentucky\n\nAccelerated training algorithms, such as adaptive learning rates and various normalization methods, are widely used in deep learning but not fully understood. When regularization is introduced, standard optimizers like adaptive learning rates may not perform effectively. This raises the need for …

LOCATION:JWB 335

URL:https://www.math.utah.edu/research/colloquia/2024-10-17-qiang-ye/
END:VEVENT
END:VCALENDAR