{"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/accelerating-neural-architecture-search-using","title":"Accelerating Neural Architecture Search using Performance Prediction","arxiv_id":"1705.10823","date":"2017-05-30","proceeding":"ICLR 2018 1","authors":["Bowen Baker","Otkrist Gupta","Ramesh Raskar","Nikhil Naik"],"abstract":"Methods for neural network hyperparameter optimization and meta-modeling are\ncomputationally expensive due to the need to train a large number of model\nconfigurations. In this paper, we show that standard frequentist regression\nmodels can predict the final performance of partially trained model\nconfigurations using features based on network architectures, hyperparameters,\nand time-series validation performance data. We empirically show that our\nperformance prediction models are much more effective than prominent Bayesian\ncounterparts, are simpler to implement, and are faster to train. Our models can\npredict final performance in both visual classification and language modeling\ndomains, are effective for predicting performance of drastically varying model\narchitectures, and can even generalize between model classes. Using these\nprediction models, we also propose an early stopping method for hyperparameter\noptimization and meta-modeling, which obtains a speedup of a factor up to 6x in\nboth hyperparameter optimization and meta-modeling. Finally, we empirically\nshow that our early stopping method can be seamlessly incorporated into both\nreinforcement learning-based architecture selection algorithms and bandit based\nsearch methods. Through extensive experimentation, we empirically show our\nperformance prediction models and early stopping algorithm are state-of-the-art\nin terms of prediction accuracy and speedup achieved while still identifying\nthe optimal model configurations.","url_abs":"http://arxiv.org/abs/1705.10823v2","url_pdf":"http://arxiv.org/pdf/1705.10823v2.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":"accelerating-neural-architecture-search-using","repo_url":"https://github.com/bowenbaker/metaqnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"unanswered"}},{"paper_slug":"accelerating-neural-architecture-search-using","repo_url":"https://github.com/nikdnaik/accelerating_nas-1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[{"method_slug":"early-stopping","method_name":"Early Stopping"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1705.10823","atlas_url":"https://app.syntology.ai/?focus=1705.10823","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":"1705.10823"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1705.10823\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1705.10823"},"call":"get_concepts_for_paper(arxiv_id=\"1705.10823\")"}],"by_repo":[{"repo":"bowenbaker/metaqnn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"nikdnaik/accelerating_nas-1","kind":"listed","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":"cc8083eaa579de4b08139c875855ff595b0c20c51585e83b759823fc8140c1ce","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}