# Towards Efficient Evaluation of Evolutionary Transfer Optimization: Case Studies on Task-Parameterized Applications

arXiv: https://arxiv.org/abs/2609.05040 · HTML: https://mlsanity.com/paper/2609.05040/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 21 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Builds on (most cited first, 6 of 6)

- [Quality Diversity for Multi-task Optimization](https://mlsanity.com/paper/2003.04407/) (2020)
- [EvoX: A Distributed GPU-accelerated Framework for Scalable Evolutionary Computation](https://mlsanity.com/paper/2301.12457/) (2023)
- [Half a Dozen Real-World Applications of Evolutionary Multitasking, and More](https://mlsanity.com/paper/2109.13101/) (2021)
- [A Scalable Test Problem Generator for Sequential Transfer Optimization](https://mlsanity.com/paper/2304.08503/) (2023)
- [(θl, θu)-Parametric Multi-Task Optimization: Joint Search in Solution and Infinite Task Spaces](https://mlsanity.com/paper/2503.08394/) (2025)
- [A Theoretical Analysis of Analogy-Based Evolutionary Transfer Optimization](https://mlsanity.com/paper/2503.21156/) (2025)

## Abstract (arXiv)

As evolutionary transfer optimization (ETO) scales to larger collections of related tasks, problem evaluation can become a major source of runtime growth. This work studies problem-side evaluation scaling in task-parameterized applications and reformulates application-specific serial computations into forms suitable for parallel execution. We organize evaluation scaling into two levels: the number of evaluated tasks and the workload within each task. In multi-task optimization, matrix-recursive kinematic-arm evaluation is reformulated using an accumulation-matrix representation of cumulative link directions. In sequential transfer optimization, pointwise B-spline trajectory evaluation is reformulated using a blending-matrix representation for trajectory and collision computations. Both reformulations maintain close numerical agreement with their reference evaluations and substantially reduce runtime, yielding 256.72× and 93.91× end-to-end speedups, respectively. These results demonstrate problem-side reformulation as a practical route toward scalable ETO. Both application implementations and experimental scripts are released as open source to support reproducibility and reuse.