{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/neural-architecture-search-with-bayesian","title":"Neural Architecture Search with Bayesian Optimisation and Optimal Transport","arxiv_id":"1802.07191","date":"2018-02-11","proceeding":"NeurIPS 2018 12","authors":["Kirthevasan Kandasamy","Willie Neiswanger","Jeff Schneider","Barnabas Poczos","Eric Xing"],"abstract":"Bayesian Optimisation (BO) refers to a class of methods for global\noptimisation of a function $f$ which is only accessible via point evaluations.\nIt is typically used in settings where $f$ is expensive to evaluate. A common\nuse case for BO in machine learning is model selection, where it is not\npossible to analytically model the generalisation performance of a statistical\nmodel, and we resort to noisy and expensive training and validation procedures\nto choose the best model. Conventional BO methods have focused on Euclidean and\ncategorical domains, which, in the context of model selection, only permits\ntuning scalar hyper-parameters of machine learning algorithms. However, with\nthe surge of interest in deep learning, there is an increasing demand to tune\nneural network \\emph{architectures}. In this work, we develop NASBOT, a\nGaussian process based BO framework for neural architecture search. To\naccomplish this, we develop a distance metric in the space of neural network\narchitectures which can be computed efficiently via an optimal transport\nprogram. This distance might be of independent interest to the deep learning\ncommunity as it may find applications outside of BO. We demonstrate that NASBOT\noutperforms other alternatives for architecture search in several cross\nvalidation based model selection tasks on multi-layer perceptrons and\nconvolutional neural networks.","url_abs":"http://arxiv.org/abs/1802.07191v3","url_pdf":"http://arxiv.org/pdf/1802.07191v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"neural-architecture-search-with-bayesian","repo_url":"https://github.com/kirthevasank/nasbot","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"bayesian-optimisation","task_name":"Bayesian Optimisation"},{"task_slug":"model-selection","task_name":"Model Selection"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201","task":"Neural Architecture Search","dataset":"NAS-Bench-201, ImageNet-16-120","model":"NASBOT","rank_in_archive_order":9,"of":49,"metrics":{"Accuracy (Test)":"46.37","Search time (s)":"75600"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.07191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.07191"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kirthevasank/nasbot","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ef50c08f1ff46b68","entry":"compute_average_prediction_error","repo":"kirthevasank/nasbot","repo_kind":"official","path":"gp/unittest_gp_core.py","file_url":"https://github.com/kirthevasank/nasbot/blob/HEAD/gp/unittest_gp_core.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef50c08f1ff46b68"}},{"code_sha256_prefix":"a6a4abcc2973fed9","entry":"compute_num_channels_at_each_layer","repo":"kirthevasank/nasbot","repo_kind":"official","path":"nn/neural_network.py","file_url":"https://github.com/kirthevasank/nasbot/blob/HEAD/nn/neural_network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a6a4abcc2973fed9"}},{"code_sha256_prefix":"86331e4a8e28234f","entry":"get_layer_parents","repo":"kirthevasank/nasbot","repo_kind":"official","path":"cg/cifar/cifar10_model.py","file_url":"https://github.com/kirthevasank/nasbot/blob/HEAD/cg/cifar/cifar10_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"86331e4a8e28234f"}},{"code_sha256_prefix":"bd6937e07a692c60","entry":"get_mean_func_from_options","repo":"kirthevasank/nasbot","repo_kind":"official","path":"gp/gp_core.py","file_url":"https://github.com/kirthevasank/nasbot/blob/HEAD/gp/gp_core.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd6937e07a692c60"}},{"code_sha256_prefix":"f76525418cf49d82","entry":"get_model_fn","repo":"kirthevasank/nasbot","repo_kind":"official","path":"cg/run_tensorflow.py","file_url":"https://github.com/kirthevasank/nasbot/blob/HEAD/cg/run_tensorflow.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f76525418cf49d82"}},{"code_sha256_prefix":"94bf803b1d0a42f0","entry":"get_noise_var_from_options_and_hyperparams","repo":"kirthevasank/nasbot","repo_kind":"official","path":"gp/gp_core.py","file_url":"https://github.com/kirthevasank/nasbot/blob/HEAD/gp/gp_core.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"94bf803b1d0a42f0"}},{"code_sha256_prefix":"f77a8e0b35483ac1","entry":"is_a_conv_layer_label","repo":"kirthevasank/nasbot","repo_kind":"official","path":"nn/neural_network.py","file_url":"https://github.com/kirthevasank/nasbot/blob/HEAD/nn/neural_network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f77a8e0b35483ac1"}},{"code_sha256_prefix":"72ee2c78a10ad1ad","entry":"is_a_pooling_layer_label","repo":"kirthevasank/nasbot","repo_kind":"official","path":"nn/neural_network.py","file_url":"https://github.com/kirthevasank/nasbot/blob/HEAD/nn/neural_network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"72ee2c78a10ad1ad"}},{"code_sha256_prefix":"ddfb882c2b659e1a","entry":"mlp_definition","repo":"kirthevasank/nasbot","repo_kind":"official","path":"cg/run_tensorflow.py","file_url":"https://github.com/kirthevasank/nasbot/blob/HEAD/cg/run_tensorflow.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ddfb882c2b659e1a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}