面向 RL 驱动硬件感知 NAS 的可控覆盖率在线保形校准

View PDF HTML (experimental)

Abstract: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 $\delta$ 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 this https URL.

Subjects:	Machine Learning (cs.LG)
Cite as:	arXiv:2610.03127 [cs.LG]
	(or arXiv:2610.03127v1 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2610.03127 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Pedro Brandimarte [view email]
[v1] Fri, 2 Oct 2026 10:47:58 UTC (143 KB)