Bencher: Simple and Reproducible Benchmarking for Black-Box Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Papenmeier, Leonard, Nardi, Luigi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918036531838976
author Papenmeier, Leonard
Nardi, Luigi
author_facet Papenmeier, Leonard
Nardi, Luigi
contents We present Bencher, a modular benchmarking framework for black-box optimization that fundamentally decouples benchmark execution from optimization logic. Unlike prior suites that focus on combining many benchmarks in a single project, Bencher introduces a clean abstraction boundary: each benchmark is isolated in its own virtual Python environment and accessed via a unified, version-agnostic remote procedure call (RPC) interface. This design eliminates dependency conflicts and simplifies the integration of diverse, real-world benchmarks, which often have complex and conflicting software requirements. Bencher can be deployed locally or remotely via Docker or on high-performance computing (HPC) clusters via Singularity, providing a containerized, reproducible runtime for any benchmark. Its lightweight client requires minimal setup and supports drop-in evaluation of 80 benchmarks across continuous, categorical, and binary domains.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21321
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bencher: Simple and Reproducible Benchmarking for Black-Box Optimization
Papenmeier, Leonard
Nardi, Luigi
Machine Learning
We present Bencher, a modular benchmarking framework for black-box optimization that fundamentally decouples benchmark execution from optimization logic. Unlike prior suites that focus on combining many benchmarks in a single project, Bencher introduces a clean abstraction boundary: each benchmark is isolated in its own virtual Python environment and accessed via a unified, version-agnostic remote procedure call (RPC) interface. This design eliminates dependency conflicts and simplifies the integration of diverse, real-world benchmarks, which often have complex and conflicting software requirements. Bencher can be deployed locally or remotely via Docker or on high-performance computing (HPC) clusters via Singularity, providing a containerized, reproducible runtime for any benchmark. Its lightweight client requires minimal setup and supports drop-in evaluation of 80 benchmarks across continuous, categorical, and binary domains.
title Bencher: Simple and Reproducible Benchmarking for Black-Box Optimization
topic Machine Learning
url https://arxiv.org/abs/2505.21321