{"slug": "rank-reliable-teacher-guided-fitness-approximation-for-expensive-evolutionary-a", "title": "Rank-Reliable Teacher-Guided Fitness Approximation for Expensive Evolutionary Optimization: A TinyML Architecture Search Study", "summary": "A pretrained teacher-guided low-fidelity framework, TGL-NSGA-II, achieved measured Kendall-τ values of 0.74 on keyword spotting and 0.62 on bird-call classification, exceeding predicted lower bounds of 0.60 and 0.46, according to an arXiv paper (arXiv:2609.30553v1). Joint stratification reduced proxy-score variance by 41% versus random evaluation, while selective teacher mismatch increased differential bias and cut Kendall-τ to 0.41. Under a constrained evaluation budget, TGL-NSGA-II delivered the largest mean hypervolume and smallest generational distance on keyword spotting, the lowest mean false-positive rate on BirdCLEF, and ran 2.2x faster than full NSGA-II.", "body_md": "arXiv:2609.30553v1 Announce Type: new \nAbstract: Expensive evolutionary search does not always need an exact fitness estimate for every candidate. It often needs a reliable answer to a simpler question: which candidate is better? We address this need through Teacher-Guided Learning NSGA-II (TGL-NSGA-II), a low-fidelity framework for constrained Tiny Machine Learning (TinyML) neural architecture search. A pretrained teacher organizes samples into strata defined jointly by difficulty and class. Each candidate then undergoes KD-Lite, a short and capped knowledge-distillation procedure on a compact training set, before being scored on a separate stratified evaluation set. This teacher-guided score is fused with a Gaussian-process surrogate to select candidates for full evaluation. For a fixed candidate population, we analyse evaluation variance, score concentration, pairwise rank inversion, expected Kendall-$\\tau$, first-front identification, and hypervolume perturbation. We also derive a variance-aware fusion weight and a capacity-adaptive distillation rule. On keyword spotting and bird-call classification, the measured Kendall-$\\tau$ values are 0.74 and 0.62, exceeding the corresponding predicted lower bounds of 0.60 and 0.46. Joint stratification reduces proxy-score variance by 41% relative to random evaluation. Selective teacher mismatch, in contrast, increases differential bias and reduces Kendall-$\\tau$ to 0.41. Under a constrained evaluation budget, TGL-NSGA-II achieves the largest mean hypervolume and smallest generational distance on keyword spotting, records the lowest mean false-positive rate on BirdCLEF, and runs 2.2x faster than full NSGA-II. These guarantees apply to population-level low-fidelity evaluation and do not establish convergence of the complete evolutionary trajectory.", "url": "https://wpnews.pro/news/rank-reliable-teacher-guided-fitness-approximation-for-expensive-evolutionary-a", "canonical_source": "https://arxiv.org/abs/2609.30553", "published_at": "2026-09-28 04:00:00+00:00", "updated_at": "2026-09-28 04:20:02.301744+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "neural-networks"], "entities": ["TGL-NSGA-II", "NSGA-II", "arXiv", "BirdCLEF", "TinyML"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/rank-reliable-teacher-guided-fitness-approximation-for-expensive-evolutionary-a", "markdown": "https://wpnews.pro/news/rank-reliable-teacher-guided-fitness-approximation-for-expensive-evolutionary-a.md", "text": "https://wpnews.pro/news/rank-reliable-teacher-guided-fitness-approximation-for-expensive-evolutionary-a.txt", "jsonld": "https://wpnews.pro/news/rank-reliable-teacher-guided-fitness-approximation-for-expensive-evolutionary-a.jsonld"}}