{"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/on-constrained-optimization-in-differentiable","title":"DARTS-PRIME: Regularization and Scheduling Improve Constrained Optimization in Differentiable NAS","arxiv_id":"2106.11655","date":"2021-06-22","proceeding":null,"authors":["Kaitlin Maile","Erwan Lecarpentier","Hervé Luga","Dennis G. Wilson"],"abstract":"Differentiable Architecture Search (DARTS) is a recent neural architecture search (NAS) method based on a differentiable relaxation. Due to its success, numerous variants analyzing and improving parts of the DARTS framework have recently been proposed. By considering the problem as a constrained bilevel optimization, we present and analyze DARTS-PRIME, a variant including improvements to architectural weight update scheduling and regularization towards discretization. We propose a dynamic schedule based on per-minibatch network information to make architecture updates more informed, as well as proximity regularization to promote well-separated discretization. Our results in multiple domains show that DARTS-PRIME improves both performance and reliability, comparable to state-of-the-art in differentiable NAS.","url_abs":"https://arxiv.org/abs/2106.11655v3","url_pdf":"https://arxiv.org/pdf/2106.11655v3.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":"bilevel-optimization","task_name":"Bilevel Optimization"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"scheduling","task_name":"Scheduling"}],"methods":[{"method_slug":"darts","method_name":"DARTS"},{"method_slug":"proximity-regularization","method_name":"Proximity Regularization"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/neural-architecture-search-on-cifar-10","task":"Neural Architecture Search","dataset":"CIFAR-10","model":"DARTS-PRIME","rank_in_archive_order":29,"of":41,"metrics":{"Parameters":"3.7M","Search Time (GPU days)":"0.5","Top-1 Error Rate":"2.62%"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-cifar-100-1","task":"Neural Architecture Search","dataset":"CIFAR-100","model":"DARTS-PRIME","rank_in_archive_order":10,"of":13,"metrics":{"PARAMS":"3.16M","Percentage Error":"17.44"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}