# Speedy Performance Estimation for Neural Architecture Search

arXiv: https://arxiv.org/abs/2006.04492 · HTML: https://mlsanity.com/paper/2006.04492/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2020.

## Built on by (most cited first, 24 of 24)

- [NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxies](https://mlsanity.com/paper/2210.03230/) (2022)
- [A Primer on Bayesian Neural Networks: Review and Debates](https://mlsanity.com/paper/2309.16314/) (2023)
- [Early Stopping Against Label Noise Without Validation Data](https://mlsanity.com/paper/2502.07551/) (2025)
- [From Memorization to Creativity: LLM as a Designer of Novel Neural Architectures](https://mlsanity.com/paper/2601.02997/) (2026)
- [Hyperparameter Optimization through Neural Network Partitioning](https://mlsanity.com/paper/2304.14766/) (2023)
- [Resource-Efficient Iterative LLM-Based NAS with Feedback Memory](https://mlsanity.com/paper/2603.12091/) (2026)
- [CAP: A Context-Aware Neural Predictor for NAS](https://mlsanity.com/paper/2406.02056/) (2024)
- [Efficient Deep Learning Infrastructures for Embedded Computing Systems: A Comprehensive Survey and Future Envision](https://mlsanity.com/paper/2411.01431/) (2024)
- [Architecture-Aware Learning Curve Extrapolation via Graph Ordinary Differential Equation](https://mlsanity.com/paper/2412.15554/) (2024)
- [Exploring the Intersection between Neural Architecture Search and Continual Learning](https://mlsanity.com/paper/2206.05625/) (2022)
- [Cold Posteriors through PAC-Bayes](https://mlsanity.com/paper/2206.11173/) (2022)
- [Leveraging Unlabeled Data to Track Memorization](https://mlsanity.com/paper/2212.04461/) (2022)
- [Fine-Tuned In-Context Learners for Efficient Adaptation](https://mlsanity.com/paper/2512.19879/) (2025)
- [Multi-objective Differentiable Neural Architecture Search](https://mlsanity.com/paper/2402.18213/) (2024)
- [CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search](https://mlsanity.com/paper/2609.11884/) (2026)
- [DARTS without a Validation Set: Optimizing the Marginal Likelihood](https://mlsanity.com/paper/2112.13023/) (2021)
- [EmProx: Neural Network Performance Estimation For Neural Architecture Search](https://mlsanity.com/paper/2206.05972/) (2022)
- [ECToNAS: Evolutionary Cross-Topology Neural Architecture Search](https://mlsanity.com/paper/2403.05123/) (2024)
- [Manifold Metric: A Loss Landscape Approach for Predicting Model Performance](https://mlsanity.com/paper/2405.15895/) (2024)
- [Is Supervised Learning Really That Different from Unsupervised?](https://mlsanity.com/paper/2505.11006/) (2025)
- [RiPPLE: Cross-Space Performance Prediction from Early Training for Neural Architecture Search](https://mlsanity.com/paper/2609.12418/) (2026)
- [EvoTreeNAD: Genealogy-Guided Evolution for LLM-Driven Neural Architecture Discovery](https://mlsanity.com/paper/2609.29016/) (2026)
- [Rank-Reliable Teacher-Guided Fitness Approximation for Expensive Evolutionary Optimization: A TinyML Architecture Search Study](https://mlsanity.com/paper/2609.30553/) (2026)
- [LESS: Lightweight Evolutionary Supernet Search in Minutes](https://mlsanity.com/paper/2610.01468/) (2026)

## Abstract (arXiv)

Reliable yet efficient evaluation of generalisation performance of a proposed architecture is crucial to the success of neural architecture search (NAS). Traditional approaches face a variety of limitations: training each architecture to completion is prohibitively expensive, early stopped validation accuracy may correlate poorly with fully trained performance, and model-based estimators require large training sets. We instead propose to estimate the final test performance based on a simple measure of training speed. Our estimator is theoretically motivated by the connection between generalisation and training speed, and is also inspired by the reformulation of a PAC-Bayes bound under the Bayesian setting. Our model-free estimator is simple, efficient, and cheap to implement, and does not require hyperparameter-tuning or surrogate training before deployment. We demonstrate on various NAS search spaces that our estimator consistently outperforms other alternatives in achieving better correlation with the true test performance rankings. We further show that our estimator can be easily incorporated into both query-based and one-shot NAS methods to improve the speed or quality of the search.