{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/layernas-neural-architecture-search-in","title":"LayerNAS: Neural Architecture Search in Polynomial Complexity","arxiv_id":"2304.11517","date":"2023-04-23","proceeding":null,"authors":["Yicheng Fan","Dana Alon","Jingyue Shen","Daiyi Peng","Keshav Kumar","Yun Long","Xin Wang","Fotis Iliopoulos","Da-Cheng Juan","Erik Vee"],"abstract":"Neural Architecture Search (NAS) has become a popular method for discovering effective model architectures, especially for target hardware. As such, NAS methods that find optimal architectures under constraints are essential. In our paper, we propose LayerNAS to address the challenge of multi-objective NAS by transforming it into a combinatorial optimization problem, which effectively constrains the search complexity to be polynomial. For a model architecture with $L$ layers, we perform layerwise-search for each layer, selecting from a set of search options $\\mathbb{S}$. LayerNAS groups model candidates based on one objective, such as model size or latency, and searches for the optimal model based on another objective, thereby splitting the cost and reward elements of the search. This approach limits the search complexity to $ O(H \\cdot |\\mathbb{S}| \\cdot L) $, where $H$ is a constant set in LayerNAS. Our experiments show that LayerNAS is able to consistently discover superior models across a variety of search spaces in comparison to strong baselines, including search spaces derived from NATS-Bench, MobileNetV2 and MobileNetV3.","url_abs":"https://arxiv.org/abs/2304.11517v1","url_pdf":"https://arxiv.org/pdf/2304.11517v1.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":[],"tasks":[{"task_slug":"combinatorial-optimization","task_name":"Combinatorial Optimization"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"hard-swish","method_name":"Hard Swish"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"relu6","method_name":"ReLU6"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"squeeze-and-excitation-block","method_name":"Squeeze-and-Excitation Block"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"LayerNAS-600M","rank_in_archive_order":45,"of":135,"metrics":{"MACs":"627M","Params":"9.7M","Top-1 Error Rate":"21.4"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"LayerNAS-300M","rank_in_archive_order":75,"of":135,"metrics":{"MACs":"322M","Params":"5.2M","Top-1 Error Rate":"22.9"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"LayerNAS-220M","rank_in_archive_order":106,"of":135,"metrics":{"MACs":"229M","Params":"5.1M","Top-1 Error Rate":"24.4"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"LayerNAS-60M","rank_in_archive_order":129,"of":135,"metrics":{"MACs":"61M","Params":"3.7M","Top-1 Error Rate":"31"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-101","task":"Neural Architecture Search","dataset":"NAS-Bench-101","model":"LayerNAS","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy (%)":"94.26%"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench-size-1","task":"Neural Architecture Search","dataset":"NATS-Bench Size, CIFAR-10","model":"LayerNAS","rank_in_archive_order":5,"of":5,"metrics":{"Test Accuracy":"93.2","Validation Accuracy":"0.844"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench-size-2","task":"Neural Architecture Search","dataset":"NATS-Bench Size, CIFAR-100","model":"LayerNAS","rank_in_archive_order":5,"of":5,"metrics":{"Test Accuracy":"70.64","Validation Accuracy":"60.67"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench-size-3","task":"Neural Architecture Search","dataset":"NATS-Bench Size, ImageNet16-120","model":"LayerNAS","rank_in_archive_order":4,"of":4,"metrics":{"Test Accuracy":"45.37","Validation Accuracy":"38.12"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench-1","task":"Neural Architecture Search","dataset":"NATS-Bench Topology, CIFAR-10","model":"LayerNAS","rank_in_archive_order":1,"of":11,"metrics":{"Test Accuracy":"94.34±0.12"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench-2","task":"Neural Architecture Search","dataset":"NATS-Bench Topology, CIFAR-100","model":"LayerNAS","rank_in_archive_order":1,"of":11,"metrics":{"Test Accuracy":"73.01±0.63"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench","task":"Neural Architecture Search","dataset":"NATS-Bench Topology, ImageNet16-120","model":"LayerNAS","rank_in_archive_order":1,"of":11,"metrics":{"Test Accuracy":"46.58±0.59"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.11517","atlas_url":"https://app.syntology.ai/?focus=2304.11517","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2304.11517"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2304.11517\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2304.11517"},"call":"get_concepts_for_paper(arxiv_id=\"2304.11517\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"410a3663ba506ab932009e90188209a26727e864d45f3e67dcb30abc7dcacbdc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}