{"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/noisy-differentiable-architecture-search","title":"Noisy Differentiable Architecture Search","arxiv_id":"2005.03566","date":"2020-05-07","proceeding":null,"authors":["Xiangxiang Chu","Bo Zhang"],"abstract":"Simplicity is the ultimate sophistication. Differentiable Architecture Search (DARTS) has now become one of the mainstream paradigms of neural architecture search. However, it largely suffers from the well-known performance collapse issue due to the aggregation of skip connections. It is thought to have overly benefited from the residual structure which accelerates the information flow. To weaken this impact, we propose to inject unbiased random noise to impede the flow. We name this novel approach NoisyDARTS. In effect, a network optimizer should perceive this difficulty at each training step and refrain from overshooting, especially on skip connections. In the long run, since we add no bias to the gradient in terms of expectation, it is still likely to converge to the right solution area. We also prove that the injected noise plays a role in smoothing the loss landscape, which makes the optimization easier. Our method features extreme simplicity and acts as a new strong baseline. We perform extensive experiments across various search spaces, datasets, and tasks, where we robustly achieve state-of-the-art results. Our code is available at https://github.com/xiaomi-automl/NoisyDARTS.","url_abs":"https://arxiv.org/abs/2005.03566v3","url_pdf":"https://arxiv.org/pdf/2005.03566v3.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":"noisy-differentiable-architecture-search","repo_url":"https://github.com/xiaomi-automl/NoisyDARTS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"automl","task_name":"AutoML"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"NoisyDARTS-A-t","rank_in_archive_order":48,"of":265,"metrics":{"Percentage correct":"98.28"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"NoisyDARTS-a","rank_in_archive_order":75,"of":265,"metrics":{"Percentage correct":"97.61"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-cifar-10","task":"Neural Architecture Search","dataset":"CIFAR-10","model":"NoisyDARTS","rank_in_archive_order":12,"of":41,"metrics":{"FLOPS":"534M","Parameters":"3.25M","Search Time (GPU days)":"0.25","Top-1 Error Rate":"2.39%"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"NoisyDARTS-A","rank_in_archive_order":54,"of":135,"metrics":{"Accuracy":"77.9","MACs":"449M","Params":"5.5M","Top-1 Error Rate":"22.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2005.03566","atlas_url":"https://app.syntology.ai/?focus=2005.03566","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":"2005.03566"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2005.03566\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2005.03566"},"call":"get_concepts_for_paper(arxiv_id=\"2005.03566\")"}],"by_repo":[{"repo":"xiaomi-automl/NoisyDARTS","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"3a1c9fa604c8970d05d2cf148ed98e95d294c0dfb571cc7b1e26c3ce749fff3b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}