{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T02:04:07Z","timestamp":1784081047631,"version":"3.55.0"},"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>First-order optimization algorithms have been proven prominent in deep learning. In particu- lar, algorithms such as RMSProp and Adam are extremely popular. However, recent works have pointed out the lack of \u201clong-term memory\u201d in Adam-like algorithms, which could hamper their performance and lead to divergence. In our study, we observe that there are benefits of weighting more of the past gradients when designing the adaptive learning rate. We therefore propose an algorithm called the Nostalgic Adam (NosAdam) with theoretically guaranteed convergence at the best known convergence rate. NosAdam can be regarded as a fix to the non-convergence issue of Adam in alternative to the recent work of [Reddi et al., 2018]. Our preliminary numerical experiments show that NosAdam is a promising alternative al- gorithm to Adam. The proofs, code and other supplementary materials are already released.<\/jats:p>","DOI":"10.24963\/ijcai.2019\/355","type":"proceedings-article","created":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T03:46:05Z","timestamp":1564285565000},"page":"2556-2562","source":"Crossref","is-referenced-by-count":34,"title":["Nostalgic Adam: Weighting More of the Past Gradients When Designing the Adaptive Learning Rate"],"prefix":"10.24963","author":[{"given":"Haiwen","family":"Huang","sequence":"first","affiliation":[{"name":"School of Mathematical Sciences, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Dong","sequence":"additional","affiliation":[{"name":"Beijing International Center for Mathematical Research, Peking University"},{"name":"Center for Data Science, Peking University"},{"name":"Laboratory for Biomedical Image Analysis, Beijing Institute of Big Data Research, Beijing"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}","theme":"Artificial Intelligence","location":"Macao, China","acronym":"IJCAI-2019","number":"28","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2019,8,10]]},"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":"2019-07-28T03:48:45Z","timestamp":1564285725000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2019\/355"}},"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\/355","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}