{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T09:06:51Z","timestamp":1773133611861,"version":"3.50.1"},"reference-count":22,"publisher":"World Scientific Pub Co Pte Ltd","issue":"05","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Asia Pac. J. Oper. Res."],"published-print":{"date-parts":[[2021,10]]},"abstract":"<jats:p> Privacy-preserving empirical risk minimization model is crucial for the increasingly frequent setting of analyzing personal data, such as medical records, financial records, etc. Due to its advantage of a rigorous mathematical definition, differential privacy has been widely used in privacy protection and has received much attention in recent years of privacy protection. With the advantages of iterative algorithms in solving a variety of problems, like empirical risk minimization, there have been various works in the literature that target differentially private iteration algorithms, especially the adaptive iterative algorithm. However, the solution of the final model parameters is imprecise because of the vast privacy budget spending on the step size search. In this paper, we first proposed a novel adaptive differential privacy algorithm that does not require the privacy budget for step size determination. Then, through the theoretical analyses, we prove that our proposed algorithm satisfies differential privacy, and their solutions achieve sufficient accuracy by infinite steps. Furthermore, numerical analysis is performed based on real-world databases. The results indicate that our proposed algorithm outperforms existing algorithms for model fitting in terms of accuracy. <\/jats:p>","DOI":"10.1142\/s021759592140011x","type":"journal-article","created":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T15:08:25Z","timestamp":1618844905000},"source":"Crossref","is-referenced-by-count":2,"title":["A Novel Adaptive Differential Privacy Algorithm for Empirical Risk Minimization"],"prefix":"10.1142","volume":"38","author":[{"given":"Kaili","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Operations Research and Information Engineering, Beijing University of Technology, Beijing 100124, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Operations Research and Information Engineering, Beijing University of Technology, Beijing 100124, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Civil and Transportation Engineering, Beijing University of Civil Engineering and Architecture, Beijing 102616, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibin","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Management Science, Qufu Normal University, Rizhao Shandong 276800, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2021,5,5]]},"reference":[{"key":"S021759592140011XBIB001","first-page":"308","volume-title":"Proc. 2016 ACM SIGSAC Conf. Computer and Communications Security","author":"Abadi M","year":"2016"},{"key":"S021759592140011XBIB002","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1109\/FOCS.2014.56","volume-title":"Proc. 2014 IEEE 55th Annual Symp. Foundations of Computer Science (FOCS\u201914)","author":"Bassily R","year":"2014"},{"issue":"3","key":"S021759592140011XBIB003","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1007\/s10994-013-5404-1","volume":"94","author":"Beimel A","year":"2014","journal-title":"Machine Learning"},{"key":"S021759592140011XBIB004","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1007\/978-3-662-53641-4_24","volume-title":"Theory of Cryptography Conf. (TCC\u201916)","author":"Bun M","year":"2016"},{"key":"S021759592140011XBIB005","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"issue":"3","key":"S021759592140011XBIB006","first-page":"1069","volume":"12","author":"Chaudhuri K","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"S021759592140011XBIB007","volume-title":"UCI Machine Learning Repository","author":"Dua D","year":"2019"},{"key":"S021759592140011XBIB008","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1007\/11681878_14","volume-title":"Theory of Cryptography Conf. (TCC\u201906)","author":"Dwork C","year":"2006"},{"key":"S021759592140011XBIB009","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1109\/FOCS.2010.12","volume-title":"2010 IEEE 51st Annual Symp. Foundations of Computer Science","author":"Dwork C","year":"2010"},{"key":"S021759592140011XBIB010","doi-asserted-by":"publisher","DOI":"10.1561\/0400000042"},{"key":"S021759592140011XBIB012","first-page":"1376","volume-title":"Proc. 32nd Int. Conf. Machine Learning (ICML\u201915)","author":"Kairouz P","year":"2015"},{"key":"S021759592140011XBIB013","first-page":"23: 25.1","volume-title":"Proc. 25th Annual Conf. Learning Theory","author":"Kifer D","year":"2012"},{"key":"S021759592140011XBIB014","doi-asserted-by":"crossref","first-page":"1656","DOI":"10.1145\/3219819.3220076","volume-title":"Proc. 24th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (SIGMOD\u201918)","author":"Lee J","year":"2018"},{"key":"S021759592140011XBIB015","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/978-3-662-49096-9_7","volume-title":"Theory of Cryptography Conf. (TCC\u201916)","author":"Murtagh J","year":"2016"},{"key":"S021759592140011XBIB016","doi-asserted-by":"publisher","DOI":"10.1515\/9781400873173"},{"key":"S021759592140011XBIB017","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"Robinds H","year":"1951","journal-title":"Annals of Mathematical Statistics"},{"key":"S021759592140011XBIB020","first-page":"3025","volume-title":"Advances in Neural Information Processing Systems","author":"Talwar K","year":"2015"},{"key":"S021759592140011XBIB021","first-page":"2493","volume-title":"Int. Conf. Machine Learning","author":"Wang YX","year":"2015"},{"key":"S021759592140011XBIB022","first-page":"2719","volume-title":"Advances in Neural Information Processing Systems","author":"Wang D","year":"2017"},{"key":"S021759592140011XBIB023","volume-title":"Convex Theory and Algorithms","author":"Zhang KL","year":"2020"},{"key":"S021759592140011XBIB024","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1145\/2463676.2465330","volume-title":"Proc. 2013 ACM SIGMOD Int. Conf. Management of Data (SIGMOD\u201913)","author":"Zhang J","year":"2013"},{"key":"S021759592140011XBIB025","first-page":"3922","volume-title":"Proc. 26th Int. Joint Conf. Artificial Intelligence","author":"Zhang JQ","year":"2017"}],"container-title":["Asia-Pacific Journal of Operational Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S021759592140011X","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T08:59:41Z","timestamp":1633942781000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S021759592140011X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,5]]},"references-count":22,"journal-issue":{"issue":"05","published-print":{"date-parts":[[2021,10]]}},"alternative-id":["10.1142\/S021759592140011X"],"URL":"https:\/\/doi.org\/10.1142\/s021759592140011x","relation":{},"ISSN":["0217-5959","1793-7019"],"issn-type":[{"value":"0217-5959","type":"print"},{"value":"1793-7019","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,5]]},"article-number":"2140011"}}