{"url":"/method/madgrad","slug":"madgrad","name":"MADGRAD","full_name":"Momentumized, adaptive, dual averaged gradient","full_name_withheld":false,"description_markdown":"The MADGRAD method contains a series of modifications to the [AdaGrad](https://paperswithcode.com/method/adagrad)-DA method to improve its performance on deep learning optimization problems. It gives state-of-the-art generalization performance across a diverse set of problems, including those that [Adam](https://paperswithcode.com/method/adam) normally under-performs on.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization","paper":"/paper/adaptivity-without-compromise-a-momentumized","first_author":"Aaron Defazio","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/adaptivity-without-compromise-a-momentumized"},"source":{"url":"https://arxiv.org/abs/2101.11075v3","title":"Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Stochastic Optimization","url":"/methods/category/stochastic-optimization","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/adaptivity-without-compromise-a-momentumized","title":"Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization","date":"2021-01-26","arxiv_id":"2101.11075","n_code_links":5,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/stochastic-optimization","name":"Stochastic Optimization","papers":1}],"tasks_shown":1,"n_tasks":1,"usage_by_year":[{"year":"2021","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/madgrad"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}