Saved in:
Bibliographic Details
Main Authors: Rodemann, Julian, Blocher, Hannah
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.16565
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916384098746368
author Rodemann, Julian
Blocher, Hannah
author_facet Rodemann, Julian
Blocher, Hannah
contents We introduce a framework for benchmarking optimizers according to multiple criteria over various test functions. Based on a recently introduced union-free generic depth function for partial orders/rankings, it fully exploits the ordinal information and allows for incomparability. Our method describes the distribution of all partial orders/rankings, avoiding the notorious shortcomings of aggregation. This permits to identify test functions that produce central or outlying rankings of optimizers and to assess the quality of benchmarking suites.
format Preprint
id arxiv_https___arxiv_org_abs_2402_16565
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Partial Rankings of Optimizers
Rodemann, Julian
Blocher, Hannah
Machine Learning
We introduce a framework for benchmarking optimizers according to multiple criteria over various test functions. Based on a recently introduced union-free generic depth function for partial orders/rankings, it fully exploits the ordinal information and allows for incomparability. Our method describes the distribution of all partial orders/rankings, avoiding the notorious shortcomings of aggregation. This permits to identify test functions that produce central or outlying rankings of optimizers and to assess the quality of benchmarking suites.
title Partial Rankings of Optimizers
topic Machine Learning
url https://arxiv.org/abs/2402.16565