Publication

Masked Training of Neural Networks with Partial Gradients

Martin Jaggi, Amirkeivan Mohtashami
2022
Conference Papers

Abstract

State-of-the-art training algorithms for deep learning models are based on stochastic gradient descent (SGD). Recently, many variations have been explored: perturbing parameters for better accuracy (such as in Extra-gradient), limiting SGD updates to a subset of parameters for increased efficiency (such as meProp) or a combination of both (such as Dropout). However, the convergence of these methods is often not studied in theory.

Official source

https://infoscience.epfl.ch/entities/publication/e583c296-79ec-4385-bbd5-4fef3b42c074

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.

Graph Chat

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.

Masked Training of Neural Networks with Partial Gradients

Chat with Graph Search

Topics in statistical physics of high-dimensional machine learning

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Understanding generalization and robustness in modern deep learning