aiqbench analysis
This research introduces Adaptive Conformal Inference to address the violation of exchangeability in reinforcement learning-driven neural architecture search. By replacing static quantile estimation with online feedback control, the method ensures steerable coverage guarantees while pruning 25-50% of expensive hardware evaluations without sacrificing accuracy. The approach effectively mitigates distribution shifts inherent in sequential search policies, offering a robust solution for cost-efficient model discovery.
Coverage You Can Steer: Online Conformal Calibration for RL-Driven Hardware-Aware NAS
arXiv:2610.03127v1 Announce Type: new 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 https://github.com/Vicomtech/rl-hw-nas.
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.
Machine Learning (cs.LG)
arXiv:2610.03127 [cs.LG]
(or arXiv:2610.03127v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.03127 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 291 words
Related coverage
State of the Field: AI for Epistemics and Coordination
LessWrong · Oct 2, 2026
CPATTA: Conformal Supervision Allocation For Active Test-Time Adaptation
arXiv · Sep 30, 2026
Dynamic Regime-Aware Conformal Calibration for Reliable Economic Forecast Intervals under Multiple Distribution Shifts
arXiv · Aug 20, 2026
Learning Polyhedral Conformal Sets for Robust Optimization
arXiv · Sep 9, 2026