Neural Velocity for hyperparameter tuning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dalmasso, Gianluca, Bragagnolo, Andrea, Tartaglione, Enzo, Fiandrotti, Attilio, Grangetto, Marco
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908439998889984
author Dalmasso, Gianluca
Bragagnolo, Andrea
Tartaglione, Enzo
Fiandrotti, Attilio
Grangetto, Marco
author_facet Dalmasso, Gianluca
Bragagnolo, Andrea
Tartaglione, Enzo
Fiandrotti, Attilio
Grangetto, Marco
contents Hyperparameter tuning, such as learning rate decay and defining a stopping criterion, often relies on monitoring the validation loss. This paper presents NeVe, a dynamic training approach that adjusts the learning rate and defines the stop criterion based on the novel notion of "neural velocity". The neural velocity measures the rate of change of each neuron's transfer function and is an indicator of model convergence: sampling neural velocity can be performed even by forwarding noise in the network, reducing the need for a held-out dataset. Our findings show the potential of neural velocity as a key metric for optimizing neural network training efficiently
format Preprint
id arxiv_https___arxiv_org_abs_2507_05309
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Velocity for hyperparameter tuning
Dalmasso, Gianluca
Bragagnolo, Andrea
Tartaglione, Enzo
Fiandrotti, Attilio
Grangetto, Marco
Machine Learning
Artificial Intelligence
68T05
I.2.6; I.5.1; I.5.4
Hyperparameter tuning, such as learning rate decay and defining a stopping criterion, often relies on monitoring the validation loss. This paper presents NeVe, a dynamic training approach that adjusts the learning rate and defines the stop criterion based on the novel notion of "neural velocity". The neural velocity measures the rate of change of each neuron's transfer function and is an indicator of model convergence: sampling neural velocity can be performed even by forwarding noise in the network, reducing the need for a held-out dataset. Our findings show the potential of neural velocity as a key metric for optimizing neural network training efficiently
title Neural Velocity for hyperparameter tuning
topic Machine Learning
Artificial Intelligence
68T05
I.2.6; I.5.1; I.5.4
url https://arxiv.org/abs/2507.05309