{"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/failures-of-gradient-based-deep-learning","title":"Failures of Gradient-Based Deep Learning","arxiv_id":"1703.07950","date":"2017-03-23","proceeding":"ICML 2017 8","authors":["Shai Shalev-Shwartz","Ohad Shamir","Shaked Shammah"],"abstract":"In recent years, Deep Learning has become the go-to solution for a broad\nrange of applications, often outperforming state-of-the-art. However, it is\nimportant, for both theoreticians and practitioners, to gain a deeper\nunderstanding of the difficulties and limitations associated with common\napproaches and algorithms. We describe four types of simple problems, for which\nthe gradient-based algorithms commonly used in deep learning either fail or\nsuffer from significant difficulties. We illustrate the failures through\npractical experiments, and provide theoretical insights explaining their\nsource, and how they might be remedied.","url_abs":"http://arxiv.org/abs/1703.07950v2","url_pdf":"http://arxiv.org/pdf/1703.07950v2.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":"failures-of-gradient-based-deep-learning","repo_url":"https://github.com/shakedshammah/failures_of_DL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.07950","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}