发表机构
Vicomtech Foundation, Basque Research and Technology Alliance (BRTA)（维科姆技术基金会，巴斯克研究与技术联盟（BRTA））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对硬件感知NAS中RL循环破坏共形预测可交换性假设的问题，提出在线共形校准方法，实现可操控覆盖率，在保持精度下剪除25-50%评估，并优于基线。
AI 中文摘要
硬件感知神经架构搜索（NAS）主要受评估成本制约：每个架构在奖励已知之前必须经过训练。共形预测过滤器通过剪除预测奖励上界未达阈值的候选架构来降低此成本，并提供无分布假设的保证，即最多有δ比例的候选架构被错误丢弃。该保证假设校准与测试候选架构之间具有可交换性，而周围的强化学习（RL）循环违反了这一假设：随着搜索进行，策略的提议不断改进，且在逐层构建中，每个回合内都会发生偏移。我们用在线反馈控制（自适应共形推断，包括免调参、局部自适应和组条件变体）取代一次性分位数估计，从而恢复可操控的覆盖率：调节目标即可单调且可重复地实现任意序列的覆盖率。在三个神经网络架构族以及单步和顺序搜索（三个随机种子）中，该方法将每个请求水平跟踪在约10^-3以内，同时剪除25-50%的评估且未测得精度损失，而静态校准失去对覆盖率的控制，高斯过程基线则无论请求如何都保持保守。最后，在受限测试平台上用作采集函数时，相同的乐观上界优于随机搜索，固定乐观策略已能带来增益，在线校准进一步强化了该增益。源代码可在https URL获取。
英文摘要
Hardware-aware neural architecture search (NAS) is dominated by evaluation cost: every architecture must be trained before its reward is known. Conformal-prediction filters cut this cost by pruning candidates whose predicted-reward upper bound misses a threshold, with a distribution-free guarantee that at most a fraction $δ$ are wrongly discarded. That guarantee assumes exchangeability between calibration and test candidates, which the surrounding reinforcement-learning (RL) loop violates: the policy's proposals improve as search proceeds and, in layer-by-layer construction, shift within every episode. We replace one-shot quantile estimation with online feedback control (Adaptive Conformal Inference, with tuning-free, locally-adaptive, and group-conditional variants), restoring steerable coverage: dialing the target delivers it, monotonically and reproducibly, for arbitrary sequences. Across three neural-network architecture families and both single-step and sequential search (three seeds), it tracks every requested level to within ${\sim}10^{-3}$ while pruning 25-50% of evaluations at no measured accuracy cost, whereas static calibration loses control of its coverage and a Gaussian-process baseline stays conservative regardless of the request. Finally, used as an acquisition function on one constrained testbed, the same optimistic bound beats random search, a gain that fixed optimism already carries and online calibration sharpens. The source code is available at https://github.com/Vicomtech/rl-hw-nas.
