{"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/self-concordant-analysis-of-frank-wolfe-1","title":"Self-concordant analysis of Frank-Wolfe algorithm","arxiv_id":null,"date":"2020-01-01","proceeding":"ICML 2020 1","authors":["Mathias Staudigl","Pavel Dvurechenskii","Shimrit Shtern","Kamil Safin","Petr Ostroukhov"],"abstract":"Projection-free optimization via different variants of the Frank-Wolfe (FW) method has become one of the cornerstones in optimization for machine learning since in many cases the linear minimization oracle is much cheaper to implement than projections and some sparsity needs to be preserved. In a number of applications, e.g. Poisson inverse problems or quantum state tomography, the loss is given by a\nself-concordant (SC) function having unbounded curvature, implying absence of theoretical guaranteesfor the existing FW methods. We use the\ntheory of SC functions to provide a new adaptive step size for FW methods and prove global convergence rate O(1/k), k being the iteration counter. If the problem can be represented by a local linear minimization oracle, we are the first\nto propose a FW method with linear convergence rate without assuming neither strong convexity nor a Lipschitz continuous gradient.","url_abs":"https://proceedings.icml.cc/static/paper_files/icml/2020/2292-Paper.pdf","url_pdf":"https://proceedings.icml.cc/static/paper_files/icml/2020/2292-Paper.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":"self-concordant-analysis-of-frank-wolfe-1","repo_url":"https://github.com/kamil-safin/SCFW","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"quantum-state-tomography","task_name":"Quantum State Tomography"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}