# BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search

arXiv: https://arxiv.org/abs/1910.11858 · HTML: https://mlsanity.com/paper/1910.11858/

## Key facts

- Cited by 179 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2019.

## Built on by (most cited first, 30 of 179)

- [AgentSquare: Automatic LLM Agent Search in Modular Design Space](https://mlsanity.com/paper/2410.06153/) (2024)
- [Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges](https://mlsanity.com/paper/2107.05847/) (2021)
- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [How Powerful are Performance Predictors in Neural Architecture Search?](https://mlsanity.com/paper/2104.01177/) (2021)
- [YAHPO Gym -- An Efficient Multi-Objective Multi-Fidelity Benchmark for Hyperparameter Optimization](https://mlsanity.com/paper/2109.03670/) (2021)
- [AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2301.12132/) (2023)
- [An Evaluation of Edge TPU Accelerators for Convolutional Neural Networks](https://mlsanity.com/paper/2102.10423/) (2021)
- [NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy](https://mlsanity.com/paper/2201.13396/) (2022)
- [NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxies](https://mlsanity.com/paper/2210.03230/) (2022)
- [A Survey of Techniques for Optimizing Transformer Inference](https://mlsanity.com/paper/2307.07982/) (2023)
- [NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks](https://mlsanity.com/paper/2110.05668/) (2021)
- [Stronger NAS with Weaker Predictors](https://mlsanity.com/paper/2102.10490/) (2021)
- [BORE: Bayesian Optimization by Density-Ratio Estimation](https://mlsanity.com/paper/2102.09009/) (2021)
- [Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition](https://mlsanity.com/paper/2210.09943/) (2022)
- [ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies](https://mlsanity.com/paper/2110.10423/) (2021)
- [A General Framework for User-Guided Bayesian Optimization](https://mlsanity.com/paper/2311.14645/) (2023)
- [CATE: Computation-aware Neural Architecture Encoding with Transformers](https://mlsanity.com/paper/2102.07108/) (2021)
- [NAS-Bench-x11 and the Power of Learning Curves](https://mlsanity.com/paper/2111.03602/) (2021)
- [Bayesian Generational Population-Based Training](https://mlsanity.com/paper/2207.09405/) (2022)
- [Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization](https://mlsanity.com/paper/2105.01015/) (2021)
- [A General Recipe for Likelihood-free Bayesian Optimization](https://mlsanity.com/paper/2206.13035/) (2022)
- [On Redundancy and Diversity in Cell-based Neural Architecture Search](https://mlsanity.com/paper/2203.08887/) (2022)
- [Unsupervised Sampling Promoting for Stochastic Human Trajectory Prediction](https://mlsanity.com/paper/2304.04298/) (2023)
- [Quantum Neural Architecture Search with Quantum Circuits Metric and Bayesian Optimization](https://mlsanity.com/paper/2206.14115/) (2022)
- [DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models](https://mlsanity.com/paper/2305.16943/) (2023)
- [Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization](https://mlsanity.com/paper/2106.11890/) (2021)
- [Learning Where To Look -- Generative NAS is Surprisingly Efficient](https://mlsanity.com/paper/2203.08734/) (2022)
- [Neural Architecture Design and Robustness: A Dataset](https://mlsanity.com/paper/2306.06712/) (2023)
- [AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Search](https://mlsanity.com/paper/2506.06017/) (2025)
- [Multi-conditioned Graph Diffusion for Neural Architecture Search](https://mlsanity.com/paper/2403.06020/) (2024)

## Abstract (arXiv)

Over the past half-decade, many methods have been considered for neural architecture search (NAS). Bayesian optimization (BO), which has long had success in hyperparameter optimization, has recently emerged as a very promising strategy for NAS when it is coupled with a neural predictor. Recent work has proposed different instantiations of this framework, for example, using Bayesian neural networks or graph convolutional networks as the predictive model within BO. However, the analyses in these papers often focus on the full-fledged NAS algorithm, so it is difficult to tell which individual components of the framework lead to the best performance. In this work, we give a thorough analysis of the "BO + neural predictor" framework by identifying five main components: the architecture encoding, neural predictor, uncertainty calibration method, acquisition function, and acquisition optimization strategy. We test several different methods for each component and also develop a novel path-based encoding scheme for neural architectures, which we show theoretically and empirically scales better than other encodings. Using all of our analyses, we develop a final algorithm called BANANAS, which achieves state-of-the-art performance on NAS search spaces. We adhere to the NAS research checklist (Lindauer and Hutter 2019) to facilitate best practices, and our code is available at https://github.com/naszilla/naszilla.