Research
Efficient Leakage-Free Neural Architecture Search under Leave-One-Subject-Out Evaluation
arXiv:2609.09433v1 Announce Type: new Abstract: Leave-One-Subject-Out (LOSO) evaluation estimates generalisation performance for subject-based classification but makes Neural Architecture Search (NAS)
arXiv:2609.09433v1 Announce Type: new Abstract: Leave-One-Subject-Out (LOSO) evaluation estimates generalisation performance for subject-based classification but makes Neural Architecture Search (NAS) computationally expensive because a fully nested implementation requires N independent architecture searches and, assuming approximately linear training cost, scales as O(N^2). We propose a leakage-free, block-based approach that shares NAS runs across subjects. On the BioVid Heat Pain dataset, our approach increased the mean accuracy from 82.79% to 83.39% while reducing the number of parameters by up to 99.2%.
Related
- Convergence Theory for Iterative LLM-Based Neural Architecture Search: A Parametric Cross-Entropy Framework with Closed-Form Proxy Reliability
- Leakage-Free Evaluation and Distribution-Robust Spatio-Temporal Graph Learning for Inductive Kriging
- Hybrid Quantum-Classical Neural Architecture Search
Source: arXiv cs.LG | 2026-09-10