Saved in:
Bibliographic Details
Main Authors: Shea, Betty, Schmidt, Mark
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.17954
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914849197391872
author Shea, Betty
Schmidt, Mark
author_facet Shea, Betty
Schmidt, Mark
contents We introduce the class of SO-friendly neural networks, which include several models used in practice including networks with 2 layers of hidden weights where the number of inputs is larger than the number of outputs. SO-friendly networks have the property that performing a precise line search to set the step size on each iteration has the same asymptotic cost during full-batch training as using a fixed learning. Further, for the same cost a planesearch can be used to set both the learning and momentum rate on each step. Even further, SO-friendly networks also allow us to use subspace optimization to set a learning rate and momentum rate for each layer on each iteration. We explore augmenting gradient descent as well as quasi-Newton methods and Adam with line optimization and subspace optimization, and our experiments indicate that this gives fast and reliable ways to train these networks that are insensitive to hyper-parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2406_17954
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Why Line Search when you can Plane Search? SO-Friendly Neural Networks allow Per-Iteration Optimization of Learning and Momentum Rates for Every Layer
Shea, Betty
Schmidt, Mark
Machine Learning
Optimization and Control
We introduce the class of SO-friendly neural networks, which include several models used in practice including networks with 2 layers of hidden weights where the number of inputs is larger than the number of outputs. SO-friendly networks have the property that performing a precise line search to set the step size on each iteration has the same asymptotic cost during full-batch training as using a fixed learning. Further, for the same cost a planesearch can be used to set both the learning and momentum rate on each step. Even further, SO-friendly networks also allow us to use subspace optimization to set a learning rate and momentum rate for each layer on each iteration. We explore augmenting gradient descent as well as quasi-Newton methods and Adam with line optimization and subspace optimization, and our experiments indicate that this gives fast and reliable ways to train these networks that are insensitive to hyper-parameters.
title Why Line Search when you can Plane Search? SO-Friendly Neural Networks allow Per-Iteration Optimization of Learning and Momentum Rates for Every Layer
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2406.17954