{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T15:22:11Z","timestamp":1767626531541},"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>Mini-batch gradient descent based methods are the de facto algorithms for training neural network architectures today.We introduce a mini-batch selection strategy based on submodular function maximization. Our novel submodular formulation captures the informativeness of each sample and diversity of the whole subset. We design an efficient, greedy algorithm which can give high-quality solutions to this NP-hard combinatorial optimization problem. Our extensive experiments on standard datasets show that the deep models trained using the proposed batch selection strategy provide better generalization than Stochastic Gradient Descent as well as a popular baseline sampling strategy across different learning rates, batch sizes, and distance metrics.<\/jats:p>","DOI":"10.24963\/ijcai.2019\/372","type":"proceedings-article","created":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:46:05Z","timestamp":1564299965000},"page":"2677-2683","source":"Crossref","is-referenced-by-count":16,"title":["Submodular Batch Selection for Training Deep Neural Networks"],"prefix":"10.24963","author":[{"given":"K J","family":"Joseph","sequence":"first","affiliation":[{"name":"Indian Institute of Technology, Hyderabad"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vamshi","family":"Teja R","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology, Hyderabad"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Krishnakant","family":"Singh","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology, Hyderabad"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vineeth N","family":"Balasubramanian","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology, Hyderabad"}],"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":"2019-07-28T07:48:52Z","timestamp":1564300132000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2019\/372"}},"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\/372","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}