用大模型生成可执行聚合程序，自动发现更优的零成本网络排名代理。
Bi-EZP: LLM-Guided Bilevel Program Evolution for Ensemble Zero-Cost Proxy Discovery
- 大语言模型生成带参数约束的聚合程序，实现结构与参数分离优化。
- 在NATS-Bench和DARTS上，新方法排名相关性提升10%以上。
- 适合做NAS的自动化代理选择，尤其适用于跨搜索空间场景。
零成本代理可在初始化阶段通过统计量对候选网络进行排序，避免重复训练。但不同代理捕捉特性各异，常在不同搜索空间产生不一致排名。集成代理虽能融合互补信号，但需同时优化离散聚合结构与连续系数，导致结构质量难以与参数校准分离。本文提出双层框架Bi-EZP，将二者解耦：上层由大语言模型生成针对四个互补基代理的可执行聚合程序，并设定程序特异性参数范围；下层使用协方差矩阵自适应进化策略（CMA-ES）在内层训练集上优化每个固定程序的连续参数；经校准的程序在独立验证集上通过肯德尔相关性评估，支持进化选择偏好泛化能力强的结构。在NATS-Bench与Network Design Spaces上的实验评估了跨异构搜索空间的排名性能，DARTS实验则验证下游NAS效果。结果表明，结构发现与数值校准分离的方法能有效实现自动化集成零成本代理构建。代码已开源：https://anonymous.4open.science/r/Bi-EZP-318D
原文摘要 · Abstract (English)
Zero-cost proxies enable neural architecture search (NAS) to rank candidate networks from statistics computed at initialization, avoiding repeated training. However, different proxies capture different properties and often produce inconsistent rankings across search spaces. Ensemble proxies can combine complementary signals, but automated discovery must optimize both discrete aggregation structures and their continuous coefficients, making structural quality difficult to separate from parameter calibration. We propose Bi-EZP, a bilevel framework that decouples these decisions. At the upper level, a large language model generates executable aggregation programs over four complementary base proxies with program-specific parameter bounds. At the lower level, covariance matrix adaptation evolution strategy (CMA-ES) optimizes the continuous parameters of each fixed program on an inner training split. The calibrated programs are then evaluated using Kendall's rank correlation on a disjoint validation split, enabling evolutionary selection to favor structures that generalize beyond their calibration data. Experiments on NATS-Bench and Network Design Spaces evaluate ranking performance across heterogeneous search spaces, and DARTS experiments assess downstream architecture search. Results show that separating program discovery from numerical calibration provides an effective approach to automated ensemble zero-cost proxy construction. The source code is available at: https://anonymous.4open.science/r/Bi-EZP-318D
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。