{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:06:37Z","timestamp":1760709997836},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"01","license":[{"start":{"date-parts":[[2019,7,17]],"date-time":"2019-07-17T00:00:00Z","timestamp":1563321600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.aaai.org"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Kernel selection is fundamental to the generalization performance of kernel-based learning algorithms. Approximate kernel selection is an efficient kernel selection approach that exploits the convergence property of the kernel selection criteria and the computational virtue of kernel matrix approximation. The convergence property is measured by the notion of approximate consistency. For the existing Nystr\u00f6m approximations, whose sampling distributions are independent of the specific learning task at hand, it is difficult to establish the strong approximate consistency. They mainly focus on the quality of the low-rank matrix approximation, rather than the performance of the kernel selection criterion used in conjunction with the approximate matrix. In this paper, we propose a novel Nystr\u00f6m approximate kernel selection algorithm by customizing a criterion-driven adaptive sampling distribution for the Nystr\u00f6m approximation, which adaptively reduces the error between the approximate and accurate criteria. We theoretically derive the strong approximate consistency of the proposed Nystr\u00f6m approximate kernel selection algorithm. Finally, we empirically evaluate the approximate consistency of our algorithm as compared to state-of-the-art methods.<\/jats:p>","DOI":"10.1609\/aaai.v33i01.33013462","type":"journal-article","created":{"date-parts":[[2019,9,7]],"date-time":"2019-09-07T07:35:41Z","timestamp":1567841741000},"page":"3462-3469","source":"Crossref","is-referenced-by-count":3,"title":["Approximate Kernel Selection with Strong Approximate Consistency"],"prefix":"10.1609","volume":"33","author":[{"given":"Lizhong","family":"Ding","sequence":"first","affiliation":[]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Shizhong","family":"Liao","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Peng","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Yijie","family":"Pan","sequence":"additional","affiliation":[]},{"given":"Chao","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Ling","family":"Shao","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Gao","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2019,7,17]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/4223\/4101","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/4223\/4101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T07:29:45Z","timestamp":1667806185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/4223"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,17]]},"references-count":0,"journal-issue":{"issue":"01","published-online":{"date-parts":[[2019,7,23]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v33i01.33013462","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2019,7,17]]}}}