{"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/easy-over-hard-a-case-study-on-deep-learning","title":"Easy over Hard: A Case Study on Deep Learning","arxiv_id":"1703.00133","date":"2017-03-01","proceeding":null,"authors":["Wei Fu","Tim Menzies"],"abstract":"While deep learning is an exciting new technique, the benefits of this method\nneed to be assessed with respect to its computational cost. This is\nparticularly important for deep learning since these learners need hours (to\nweeks) to train the model. Such long training time limits the ability of (a)~a\nresearcher to test the stability of their conclusion via repeated runs with\ndifferent random seeds; and (b)~other researchers to repeat, improve, or even\nrefute that original work.\n  For example, recently, deep learning was used to find which questions in the\nStack Overflow programmer discussion forum can be linked together. That deep\nlearning system took 14 hours to execute. We show here that applying a very\nsimple optimizer called DE to fine tune SVM, it can achieve similar (and\nsometimes better) results. The DE approach terminated in 10 minutes; i.e. 84\ntimes faster hours than deep learning method.\n  We offer these results as a cautionary tale to the software analytics\ncommunity and suggest that not every new innovation should be applied without\ncritical analysis. If researchers deploy some new and expensive process, that\nwork should be baselined against some simpler and faster alternatives.","url_abs":"http://arxiv.org/abs/1703.00133v2","url_pdf":"http://arxiv.org/pdf/1703.00133v2.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":"easy-over-hard-a-case-study-on-deep-learning","repo_url":"https://github.com/WeiFoo/EasyOverHard","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}