Saved in:
Bibliographic Details
Main Authors: Larsen, Kasper Green, Mathiasen, Markus Engelund, Svendsen, Clement
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.18388
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910813466394624
author Larsen, Kasper Green
Mathiasen, Markus Engelund
Svendsen, Clement
author_facet Larsen, Kasper Green
Mathiasen, Markus Engelund
Svendsen, Clement
contents We introduce a new replicable boosting algorithm which significantly improves the sample complexity compared to previous algorithms. The algorithm works by doing two layers of majority voting, using an improved version of the replicable boosting algorithm introduced by Impagliazzo et al. [2022] in the bottom layer.
format Preprint
id arxiv_https___arxiv_org_abs_2501_18388
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improved Replicable Boosting with Majority-of-Majorities
Larsen, Kasper Green
Mathiasen, Markus Engelund
Svendsen, Clement
Machine Learning
We introduce a new replicable boosting algorithm which significantly improves the sample complexity compared to previous algorithms. The algorithm works by doing two layers of majority voting, using an improved version of the replicable boosting algorithm introduced by Impagliazzo et al. [2022] in the bottom layer.
title Improved Replicable Boosting with Majority-of-Majorities
topic Machine Learning
url https://arxiv.org/abs/2501.18388