# Efficient Architecture Search under Leave-One-Subject-Out Evaluation

arXiv: https://arxiv.org/abs/2609.21457 · HTML: https://mlsanity.com/paper/2609.21457/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 33 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions](https://mlsanity.com/paper/2006.02903/) (2020)
- [Zero-Cost Proxies for Lightweight NAS](https://mlsanity.com/paper/2101.08134/) (2021)
- [Learning Where To Look -- Generative NAS is Surprisingly Efficient](https://mlsanity.com/paper/2203.08734/) (2022)
- [Transformer Encoder with Multiscale Deep Learning for Pain Classification Using Physiological Signals](https://mlsanity.com/paper/2303.06845/) (2023)
- [Hierarchically Structured Task-Agnostic Continual Learning](https://mlsanity.com/paper/2211.07725/) (2022)
- [Harmonic-NAS: Hardware-Aware Multimodal Neural Architecture Search on Resource-constrained Devices](https://mlsanity.com/paper/2309.06612/) (2023)

## Built on by (most cited first, 1 of 1)

- [Few-Shot Learning for Personalised Automated Pain Assessment](https://mlsanity.com/paper/2610.09692/) (2026)

## Abstract (arXiv)

Deep neural architectures are widely used for signal processing in automated pain assessment systems. However, architecture design has remained largely a manual task despite the potential efficiency benefits of Neural Architecture Search (NAS). Embedding NAS in a Leave-One-Subject-Out (LOSO) evaluation is computationally demanding because a fully nested implementation requires N independent architecture searches and, assuming approximately linear training cost, scales as O(N2). We propose a block-based, leakage-controlled approach that shares NAS runs between subjects, reducing the number of searches from N to B, where B ll N, dubbed PainNAS. On the BioVid Heat Pain dataset, PainNAS yields comparable subject-level accuracy with substantially fewer parameters and FLOPs.