Papers › BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search

BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search

25 Oct 2019arXiv:1910.11858archive 2025-07-28

Colin White, Willie Neiswanger, Yash Savani

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.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1910.11858")

Code

Syntology Ran 0 of 8 code samples harvested from 1 repository linked to this paper; 8 have no recorded run.

By repository: official repository: 8 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

naszilla/bananas officialmentioned in papermentioned on GitHubtfApache-2.0 report
naszilla/naszilla officialmentioned in papermentioned on GitHubtf report
ZachZhu7/banana-git mentioned on GitHubtfApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

8 samples harvested; 0 ran; 0 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

8unverified

Licence: 0 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from naszilla/bananas. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

acq_fn naszilla/bananas/acquisition_functions.py official repository unverified Apache-2.0 (permissive) · abc6e16bb94120ba · report
algo_params naszilla/bananas/params.py official repository unverified Apache-2.0 (permissive) · cf0c21c05016ec7b · report
compute_best_test_losses naszilla/bananas/nas_algorithms.py official repository unverified Apache-2.0 (permissive) · 2a3699601fc36df1 · report
mape_loss naszilla/bananas/meta_neural_net.py official repository unverified Apache-2.0 (permissive) · 3cb4846ed85433e1 · report
meta_neuralnet_params naszilla/bananas/params.py official repository unverified Apache-2.0 (permissive) · 6498b78336ea92e5 · report
mle_loss naszilla/bananas/meta_neural_net.py official repository unverified Apache-2.0 (permissive) · 94712b633dd36518 · report
random_search naszilla/bananas/nas_algorithms.py official repository unverified Apache-2.0 (permissive) · 8e77afefdb71320a · report
run_nas_algorithm naszilla/bananas/nas_algorithms.py official repository unverified Apache-2.0 (permissive) · 4ce2165ea584f056 · report

Tasks

Bayesian OptimizationHyperparameter OptimizationNeural Architecture SearchReinforcement Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 BANANAS Accuracy (Test) 46.3 #18 of 49 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 BANANAS Search time (s) 100800 #18 of 49 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Gaussian ProcessGraph Convolutional NetworksTest

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections