Bi-EZP：基于大语言模型的双层程序进化集成零成本代理发现
Bi-EZP: LLM-Guided Bilevel Program Evolution for Ensemble Zero-Cost Proxy Discovery
- School of Mathematics and Statistics, Guangdong University of Technology（广东工业大学数学与统计学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究提出Bi-EZP双层框架，通过大语言模型与CMA-ES解耦聚合结构发现和参数校准，在NATS-Bench等数据集上验证了其构建集成零成本代理的有效性
AI中文摘要：
零成本代理使神经架构搜索（NAS）能够基于初始化时计算的统计量对候选网络进行排序，避免重复训练。然而，不同代理捕获不同属性，且在不同搜索空间中常产生不一致的排序。集成代理可结合互补信号，但自动发现需同时优化离散聚合结构及其连续系数，导致结构质量难以与参数校准分离。我们提出Bi-EZP，一种解耦这些决策的双层框架：上层，大语言模型生成针对四个互补基础代理的可执行聚合程序，程序带有特定参数边界；下层，协方差矩阵自适应进化策略（CMA-ES）在内部训练拆分集上优化每个固定程序的连续参数。校准后的程序随后在不相交的验证拆分集上用Kendall秩相关进行评估，使进化选择倾向于泛化能力优于校准数据的结构。在NATS-Bench和网络设计空间（Network Design Spaces）上的实验评估了异构搜索空间的排序性能，在DARTS上的实验评估了下游架构搜索。结果表明，将程序发现与数值校准分离是构建自动集成零成本代理的有效方法。源代码可在：this https URL获取
英文摘要：
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
