Diversity-Aware Agnostic Ensemble of Sharpness Minimizers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bui, Anh, Vo, Vy, Pham, Tung, Phung, Dinh, Le, Trung
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914721100201984
author Bui, Anh
Vo, Vy
Pham, Tung
Phung, Dinh
Le, Trung
author_facet Bui, Anh
Vo, Vy
Pham, Tung
Phung, Dinh
Le, Trung
contents There has long been plenty of theoretical and empirical evidence supporting the success of ensemble learning. Deep ensembles in particular take advantage of training randomness and expressivity of individual neural networks to gain prediction diversity, ultimately leading to better generalization, robustness and uncertainty estimation. In respect of generalization, it is found that pursuing wider local minima result in models being more robust to shifts between training and testing sets. A natural research question arises out of these two approaches as to whether a boost in generalization ability can be achieved if ensemble learning and loss sharpness minimization are integrated. Our work investigates this connection and proposes DASH - a learning algorithm that promotes diversity and flatness within deep ensembles. More concretely, DASH encourages base learners to move divergently towards low-loss regions of minimal sharpness. We provide a theoretical backbone for our method along with extensive empirical evidence demonstrating an improvement in ensemble generalizability.
format Preprint
id arxiv_https___arxiv_org_abs_2403_13204
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Diversity-Aware Agnostic Ensemble of Sharpness Minimizers
Bui, Anh
Vo, Vy
Pham, Tung
Phung, Dinh
Le, Trung
Machine Learning
Computer Vision and Pattern Recognition
There has long been plenty of theoretical and empirical evidence supporting the success of ensemble learning. Deep ensembles in particular take advantage of training randomness and expressivity of individual neural networks to gain prediction diversity, ultimately leading to better generalization, robustness and uncertainty estimation. In respect of generalization, it is found that pursuing wider local minima result in models being more robust to shifts between training and testing sets. A natural research question arises out of these two approaches as to whether a boost in generalization ability can be achieved if ensemble learning and loss sharpness minimization are integrated. Our work investigates this connection and proposes DASH - a learning algorithm that promotes diversity and flatness within deep ensembles. More concretely, DASH encourages base learners to move divergently towards low-loss regions of minimal sharpness. We provide a theoretical backbone for our method along with extensive empirical evidence demonstrating an improvement in ensemble generalizability.
title Diversity-Aware Agnostic Ensemble of Sharpness Minimizers
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.13204