Large deviations in the perceptron model and consequences for active learning

Cui, H and Saglietti, L and Zdeborová, L (2021) Large deviations in the perceptron model and consequences for active learning. Machine Learning: Science and Technology, 2 (4). 045001. ISSN 2632-2153

[thumbnail of Cui_2021_Mach._Learn.__Sci._Technol._2_045001.pdf] Text
Cui_2021_Mach._Learn.__Sci._Technol._2_045001.pdf - Published Version

Download (844kB)

Abstract

Active learning (AL) is a branch of machine learning that deals with problems where unlabeled data is abundant yet obtaining labels is expensive. The learning algorithm has the possibility of querying a limited number of samples to obtain the corresponding labels, subsequently used for supervised learning. In this work, we consider the task of choosing the subset of samples to be labeled from a fixed finite pool of samples. We assume the pool of samples to be a random matrix and the ground truth labels to be generated by a single-layer teacher random neural network. We employ replica methods to analyze the large deviations for the accuracy achieved after supervised learning on a subset of the original pool. These large deviations then provide optimal achievable performance boundaries for any AL algorithm. We show that the optimal learning performance can be efficiently approached by simple message-passing AL algorithms. We also provide a comparison with the performance of some other popular active learning strategies.

Item Type: Article
Subjects: Science Repository > Multidisciplinary
Depositing User: Managing Editor
Date Deposited: 05 Jul 2023 03:55
Last Modified: 11 Oct 2023 03:59
URI: http://research.manuscritpub.com/id/eprint/2577

Actions (login required)

View Item
View Item