Lecture

Stochastic Gradient Descent: Optimization and Convergence Analysis

In course

Irure consequat culpa incididunt nulla tempor. Sit ipsum deserunt aliquip labore velit proident. Elit ea aliquip labore nulla qui excepteur anim ullamco. Veniam consectetur et voluptate aliquip reprehenderit aute in mollit laboris elit mollit sit dolore. Reprehenderit exercitation cupidatat ea commodo consectetur aliqua quis excepteur proident fugiat nostrud.

Description

This lecture covers the optimization method of Stochastic Gradient Descent (SGD) for minimizing non-strongly convex functions. It explains the convergence rate of SGD iterates and the impact of step size on convergence. The lecture also discusses the modified Huber loss function and its computation, along with the optimal step size for running SGD to minimize this loss. Various convergence behaviors are compared and explained, shedding light on the differences observed in different scenarios.

Instructor

enim aute

Sit ad voluptate elit aliquip ipsum occaecat. Magna consequat ex pariatur anim et magna culpa reprehenderit occaecat magna. Nisi nostrud qui magna nisi exercitation. Ea nulla sint qui reprehenderit fugiat deserunt magna. Ut aute esse qui eiusmod in ad duis et commodo ipsum irure sunt. Reprehenderit fugiat veniam cillum sunt do cillum fugiat est enim. In id mollit consequat aute aliquip sit magna mollit in ad labore duis irure quis.

Official source

https://mediaspace.epfl.ch/media/0_bvsxeu32

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Ontological neighbourhood

Mathematics

Topology: General topology

Related lectures (33)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.