arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.39779cs.NEcs.LG
收藏

基于子集选择多任务表示的优化器-景观交互诊断:来自钢琴指法的证据

Diagnosing Optimizer-Landscape Interaction via Representation in Subset Selection Multitasking: Evidence from Piano Fingering

Nanyang Technological University(南洋理工大学)

Ananda Phan Iman, Tingyang Wei, Chang Wook Ahn

AI总结:

本研究以钢琴指法估计为案例,通过适应度景观分析,揭示进化多任务优化中表示设计是影响知识迁移效能的关键因素。

摘要:

连续松弛常作为进化多任务优化(EMTO)的编码方案,使异构任务可在统一搜索空间内优化。但这些连续表示会从根本上重塑诱导的适应度景观,其对优化行为与知识迁移的影响仍未充分探索。本研究通过适应度景观分析,分析表示诱导的适应度景观与优化器行为的交互以填补该空白。以钢琴指法估计作为子集选择问题的代表性案例,引入若干编码变体,研究其诱导的景观如何影响EMTO下的搜索动态与解质量。分析表明,迁移效能与表示诱导的景观特征变化密切相关,而非仅与算法因素相关,强调表示设计是多任务优化中有效知识迁移的关键因素。

英文摘要:

Continuous relaxations are commonly used as an encoding scheme for evolutionary multitasking optimization (EMTO), allowing heterogeneous tasks to be optimized within a unified search space. However, these continuous representations fundamentally reshape the induced fitness landscape, and their impact on optimization behavior and knowledge transfer remains underexplored. In this work, we bridge the gap by analyzing the interaction between the representation-induced fitness landscape and optimizer behavior through fitness landscape analysis. Using piano fingering estimation as a representative case of the subset selection problem, we introduce several encoding variants and investigate how their induced landscapes influence search dynamics and solution quality under EMTO. Our analysis indicates that transfer efficacy is strongly associated with changes in representation-induced landscape characteristics, rather than algorithmic factors alone, highlighting the representation design as the key factor of effective knowledge transfer in multitasking optimization.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑