{"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/seboost-boosting-stochastic-learning-using","title":"SEBOOST - Boosting Stochastic Learning Using Subspace Optimization Techniques","arxiv_id":"1609.00629","date":"2016-09-02","proceeding":"NeurIPS 2016 12","authors":["Elad Richardson","Rom Herskovitz","Boris Ginsburg","Michael Zibulevsky"],"abstract":"We present SEBOOST, a technique for boosting the performance of existing\nstochastic optimization methods. SEBOOST applies a secondary optimization\nprocess in the subspace spanned by the last steps and descent directions. The\nmethod was inspired by the SESOP optimization method for large-scale problems,\nand has been adapted for the stochastic learning framework. It can be applied\non top of any existing optimization method with no need to tweak the internal\nalgorithm. We show that the method is able to boost the performance of\ndifferent algorithms, and make them more robust to changes in their\nhyper-parameters. As the boosting steps of SEBOOST are applied between large\nsets of descent steps, the additional subspace optimization hardly increases\nthe overall computational burden. We introduce two hyper-parameters that\ncontrol the balance between the baseline method and the secondary optimization\nprocess. The method was evaluated on several deep learning tasks, demonstrating\npromising results.","url_abs":"http://arxiv.org/abs/1609.00629v1","url_pdf":"http://arxiv.org/pdf/1609.00629v1.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":"seboost-boosting-stochastic-learning-using","repo_url":"https://github.com/eladrich/seboost","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"torch","reach":null}],"tasks":[{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}