# Searching on a Budget: HW-NAS with 10 Latency Probes Source: [Searching on a Budget: HW-NAS with 10 Latency Probes]() Collection index: [llms.txt]() Data updated: 2026-05-19T05:00:13.117Z Authors: Francesco Capuano, Gabriele Tiboni, Niccol\\\`o Cavagnero, Giuseppe Averta Published: 2025-04-01T11:15:46.000Z ## Abstract Existing hardware-aware NAS (HW-NAS) methods typically assume access to precise information circa the target device, either via analytical approximations of the post-compilation latency model, or through learned latency predictors. Such approximate approaches risk introducing estimation errors that may prove detrimental in risk-sensitive applications. In this work, we propose a two-stage HW-NAS framework, in which we first learn an architecture controller on a distribution of synthetic devices, and then directly deploy the controller on a target device. At test-time, our network controller deploys directly to the target device without relying on any pre-collected information, and only exploits direct interactions. In particular, the pre-training phase on synthetic devices enables the controller to design an architecture for the target device by interacting with it through a small number of high-fidelity latency measurements. To guarantee accessibility of our method, we only train our controller with training-free accuracy proxies, allowing us to scale the meta-training phase without incurring the overhead of full network training. We benchmark on HW-NATS-Bench, demonstrating that our method generalizes to unseen devices and searches for latency-efficient architectures by in-context adaptation using only a few real-world latency evaluations at test-time. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Hardware-aware Model Selection on iPhone 13 mini (val)](): Hardware-aware Model Selection; iPhone 13 mini (val); Median Latency (ms): 0.2261. - [Hardware-Aware Neural Architecture Search on HW-NAS-Bench CIFAR-10 (test)](): Hardware-Aware Neural Architecture Search; HW-NAS-Bench CIFAR-10 (test); Latency (%): 4.4. ## Original sources and implementation [Original paper]() [PDF]()