{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T06:33:24Z","timestamp":1747809204832},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,8]]},"abstract":"<jats:p>Asynchronous parallel stochastic optimization for non-convex\u00a0 problems\u00a0 becomes more and more\u00a0\u00a0 important in machine learning especially due to the popularity of deep learning. The Frank-Wolfe (a.k.a. conditional gradient) algorithms\u00a0 has regained much interest\u00a0 because of\u00a0 its projection-free property and the ability of handling structured constraints. However,\u00a0 our understanding of\u00a0 asynchronous stochastic Frank-Wolfe algorithms is\u00a0 extremely limited especially in the non-convex setting. To address this challenging problem, in this paper, we propose our\u00a0 asynchronous stochastic\u00a0 Frank-Wolfe algorithm (AsySFW) and\u00a0 its variance reduction version (AsySVFW) for solving the constrained non-convex optimization problems.\u00a0 More importantly, we\u00a0 prove the fast convergence rates\u00a0 of\u00a0\u00a0 AsySFW and AsySVFW in the non-convex setting. To the best of our knowledge, AsySFW and AsySVFW\u00a0 are the first asynchronous parallel stochastic algorithms with convergence guarantees for solving the constrained\u00a0 non-convex optimization problems. The\u00a0 experimental\u00a0 results on real high-dimensional gray-scale images\u00a0\u00a0 not only confirm the\u00a0 fast convergence\u00a0 of\u00a0\u00a0 our algorithms, but also show\u00a0 a near-linear speedup\u00a0 on a parallel system with shared memory due to the lock-free implementation.<\/jats:p>","DOI":"10.24963\/ijcai.2019\/104","type":"proceedings-article","created":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T03:46:05Z","timestamp":1564285565000},"page":"737-743","source":"Crossref","is-referenced-by-count":1,"title":["Asynchronous Stochastic Frank-Wolfe Algorithms for Non-Convex Optimization"],"prefix":"10.24963","author":[{"given":"Bin","family":"Gu","sequence":"first","affiliation":[{"name":"JD Finance America Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhan","family":"Xian","sequence":"additional","affiliation":[{"name":"Department of Electrical & Computer Engineering, University of Pittsburgh, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Electrical & Computer Engineering, University of Pittsburgh, USA"},{"name":"JD Finance America Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"28","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2019","name":"Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}","start":{"date-parts":[[2019,8,10]]},"theme":"Artificial Intelligence","location":"Macao, China","end":{"date-parts":[[2019,8,16]]}},"container-title":["Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T03:46:48Z","timestamp":1564285608000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2019\/104"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2019\/104","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}