{"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/agglio-global-optimization-for-locally-convex","title":"AGGLIO: Global Optimization for Locally Convex Functions","arxiv_id":"2111.03932","date":"2021-11-06","proceeding":null,"authors":["Debojyoti Dey","Bhaskar Mukhoty","Purushottam Kar"],"abstract":"This paper presents AGGLIO (Accelerated Graduated Generalized LInear-model Optimization), a stage-wise, graduated optimization technique that offers global convergence guarantees for non-convex optimization problems whose objectives offer only local convexity and may fail to be even quasi-convex at a global scale. In particular, this includes learning problems that utilize popular activation functions such as sigmoid, softplus and SiLU that yield non-convex training objectives. AGGLIO can be readily implemented using point as well as mini-batch SGD updates and offers provable convergence to the global optimum in general conditions. In experiments, AGGLIO outperformed several recently proposed optimization techniques for non-convex and locally convex objectives in terms of convergence rate as well as convergent accuracy. AGGLIO relies on a graduation technique for generalized linear models, as well as a novel proof strategy, both of which may be of independent interest.","url_abs":"https://arxiv.org/abs/2111.03932v1","url_pdf":"https://arxiv.org/pdf/2111.03932v1.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":"agglio-global-optimization-for-locally-convex","repo_url":"https://github.com/purushottamkar/agglio","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"model-optimization","task_name":"Model Optimization"},{"task_slug":"global-optimization","task_name":"global-optimization"}],"methods":[{"method_slug":"sgd","method_name":"SGD"},{"method_slug":"silu","method_name":"SiLU"}],"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}