Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Regol, Florence, Chataoui, Joud, Charpentier, Bertrand, Coates, Mark, Piantanida, Pablo, Gunnemann, Stephan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2406.14404
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916295897776128
author Regol, Florence
Chataoui, Joud
Charpentier, Bertrand
Coates, Mark
Piantanida, Pablo
Gunnemann, Stephan
author_facet Regol, Florence
Chataoui, Joud
Charpentier, Bertrand
Coates, Mark
Piantanida, Pablo
Gunnemann, Stephan
contents Machine learning models can solve complex tasks but often require significant computational resources during inference. This has led to the development of various post-training computation reduction methods that tackle this issue in different ways, such as quantization which reduces the precision of weights and arithmetic operations, and dynamic networks which adapt computation to the sample at hand. In this work, we propose a more general dynamic network that can combine both quantization and early exit dynamic network: QuEE. Our algorithm can be seen as a form of soft early exiting or input-dependent compression. Rather than a binary decision between exiting or continuing, we introduce the possibility of continuing with reduced computation. This complicates the traditionally considered early exiting problem, which we solve through a principled formulation. The crucial factor of our approach is accurate prediction of the potential accuracy improvement achievable through further computation. We demonstrate the effectiveness of our method through empirical evaluation, as well as exploring the conditions for its success on 4 classification datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2406_14404
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Predicting Probabilities of Error to Combine Quantization and Early Exiting: QuEE
Regol, Florence
Chataoui, Joud
Charpentier, Bertrand
Coates, Mark
Piantanida, Pablo
Gunnemann, Stephan
Machine Learning
Machine learning models can solve complex tasks but often require significant computational resources during inference. This has led to the development of various post-training computation reduction methods that tackle this issue in different ways, such as quantization which reduces the precision of weights and arithmetic operations, and dynamic networks which adapt computation to the sample at hand. In this work, we propose a more general dynamic network that can combine both quantization and early exit dynamic network: QuEE. Our algorithm can be seen as a form of soft early exiting or input-dependent compression. Rather than a binary decision between exiting or continuing, we introduce the possibility of continuing with reduced computation. This complicates the traditionally considered early exiting problem, which we solve through a principled formulation. The crucial factor of our approach is accurate prediction of the potential accuracy improvement achievable through further computation. We demonstrate the effectiveness of our method through empirical evaluation, as well as exploring the conditions for its success on 4 classification datasets.
title Predicting Probabilities of Error to Combine Quantization and Early Exiting: QuEE
topic Machine Learning
url https://arxiv.org/abs/2406.14404