View PDF HTML (experimental)

Abstract:This paper presents \textit{EmoPyLab}, an open-source, tensor-native Python framework for high-throughput benchmarking, analysis, and multi-criteria decision-making in multi- and many-objective optimization ($M \ge 2$). Traditional evolutionary toolchains rely on object-oriented Array-of-Structures (AoS) models that incur memory fragmentation and interpreter overhead during large campaigns, while emerging tensor engines focus primarily on single-objective neuroevolution, lacking high-dimensional analytics and post-Pareto decision support. EmoPyLab resolves this dichotomy via a contiguous Structure-of-Arrays (SoA) columnar data model executed across a 5-tier backend dispatch engine (NVIDIA CUDA, Apple MLX, JAX, CuPy, and CPU SIMD) with zero-copy persistence. The platform incorporates deductive Efficient Non-dominated Sorting ($O(M N \sqrt{N})$) and a low-discrepancy quasi-Monte Carlo Hypervolume estimator (Fast-MC HV) with Sobol sequence pruning, enabling real-time analytical evaluation in up to 15-objective spaces. Alongside 298+ metaheuristics and 916 benchmark instances, EmoPyLab embeds an in-situ Multi-Criteria Decision Making (MCDM) layer (TOPSIS, PROMETHEE II, and Compromise Programming) with decision-space back-mapping, automated non-parametric statistics (Wilcoxon, Friedman with Kendall's $W$, Vargha-Delaney $A_{12}$, Holm-Bonferroni correction), and cryptographic SHA-256 reproducibility manifests. The ecosystem provides both a memory-safe reactive graphical workspace ($< 150\text{ MB}$ RAM) and a headless CLI for distributed supercomputers. Empirical validation across 5,970 runs on the Santos Dumont Bull Sequana supercomputer confirms linear multi-core scaling and robust thread-oversubscription suppression, establishing a unified, reproducible, hardware-accelerated laboratory under the MIT license.

Submission history

From: Thiago Santos [view email]
[v1] Mon, 2 Mar 2026 00:56:32 UTC (2,220 KB)
[v2] Thu, 3 Sep 2026 19:59:00 UTC (1,067 KB)