Nested Performance Profiles for Benchmarking Software
Rasoul Hekmati, Hanieh Mirhajianmoghadam

TL;DR
This paper introduces Nested Performance Profiles, an improved benchmarking method for mathematical software that overcomes biases of traditional performance profiles, providing more reliable solver rankings.
Contribution
It proposes a novel nested approach to performance profiling that addresses biases and enhances the accuracy of solver comparisons.
Findings
The new method reliably detects top-performing solvers.
It overcomes the bias introduced by excluding the best solver.
The approach is efficient and unbiased in benchmarking.
Abstract
In order to compare and benchmark the mathematical software, the performance profiles have been introduced [1]. However, it has been proved that the algorithm is not flawless. The main issue with the performance profile is that it may rank the solvers with respect to the best solver, by excluding the best one and running the algorithm on the remaining set of the solvers, the method may rank the solvers in a different way. We characterize such systems of problems-solvers and propose an efficient and reliable algorithm to overcome this negative side effect. The proposed method is unbiased in comparing the solvers and is successful in detecting the top ones
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
