{"url":"/method/sgdw","slug":"sgdw","name":"SGDW","full_name":"SGDW","full_name_withheld":false,"description_markdown":"**SGDW** is a stochastic optimization technique that decouples [weight decay](https://paperswithcode.com/method/weight-decay) from the gradient update:\r\n\r\n$$ g\\_{t} =  \\nabla{f\\_{t}}\\left(\\theta\\_{t-1}\\right) + \\lambda\\theta\\_{t-1}$$\r\n\r\n$$ m\\_{t} =  \\beta\\_{1}m\\_{t-1} + \\eta\\_{t}\\alpha{g}\\_{t}$$\r\n\r\n$$ \\theta\\_{t} = \\theta\\_{t-1} - m\\_{t} - \\eta\\_{t}\\lambda\\theta\\_{t-1}$$","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"http://arxiv.org/abs/1711.05101v3","title":"Decoupled Weight Decay Regularization","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/jettify/pytorch-optimizer/blob/155246597d66dd774156599be0f07a8c6f7758aa/torch_optimizer/sgdw.py#L10","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Stochastic Optimization","url":"/methods/category/stochastic-optimization","pwc_aliases":[]}],"n_papers_tagged":2,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"title":"Investigating the Role of Weight Decay in Enhancing Nonconvex SGD","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/decoupled-weight-decay-regularization","title":"Decoupled Weight Decay Regularization","date":"2017-11-14","arxiv_id":"1711.05101","n_code_links":23,"syntology":{"ran":10,"of":23,"unverified":13,"pointer_only":5}}],"papers_shown":2,"tasks":[{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/image-classification","name":"image-classification","papers":1}],"tasks_shown":2,"n_tasks":2,"usage_by_year":[{"year":"2017","papers":1},{"year":"2025","papers":1}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/sgdw"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}