# Searching on a Budget: HW-NAS with 10 Latency Probes

arXiv: https://arxiv.org/abs/2504.00663 · HTML: https://mlsanity.com/paper/2504.00663/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Builds on (most cited first, 21 of 21)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Solving Rubik's Cube with a Robot Hand](https://mlsanity.com/paper/1910.07113/) (2019)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.03443/) (2018)
- [Large-Scale Evolution of Image Classifiers](https://mlsanity.com/paper/1703.01041/) (2017)
- [Neural Architecture Search without Training](https://mlsanity.com/paper/2006.04647/) (2020)
- [SMASH: One-Shot Model Architecture Search through HyperNetworks](https://mlsanity.com/paper/1708.05344/) (2017)
- [Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective](https://mlsanity.com/paper/2102.11535/) (2021)
- [NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size](https://mlsanity.com/paper/2009.00437/) (2020)
- [HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark](https://mlsanity.com/paper/2103.10584/) (2021)
- [Domain Randomization via Entropy Maximization](https://mlsanity.com/paper/2311.01885/) (2023)
- [FreeREA: Training-Free Evolution-based Architecture Search](https://mlsanity.com/paper/2207.05135/) (2022)
- [MicroNAS: Memory and Latency Constrained Hardware-Aware Neural Architecture Search for Time Series Classification on Microcontrollers](https://mlsanity.com/paper/2310.18384/) (2023)
- [Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics](https://mlsanity.com/paper/2108.11939/) (2021)

## Abstract (arXiv)

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.