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.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2504.00663 [cs.LG] |
| (or arXiv:2504.00663v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2504.00663 arXiv-issued DOI via DataCite |
From: Francesco Capuano [view email]
[v1]
Tue, 1 Apr 2025 11:15:46 UTC (3,143 KB)
[v2]
Fri, 15 May 2026 15:42:54 UTC (3,126 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。