ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate

Item #:

079017-2309

Details

DOI: https://doi.org/10.52202/079017-2309
Author(s): Keno Harada, Tomoshi Iiyama, Yusuke Iwasawa, Seong Cheol Jeong, Yutaka Matsuo, Gouki Minegishi, Go Nagahara, Yuta Oshima, Masahiro Suzuki, Shohei Taniguchi
Pages: 72438-72474 (37 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/079017-2309
Author(s): Keno Harada, Tomoshi Iiyama, Yusuke Iwasawa, Seong Cheol Jeong, Yutaka Matsuo, Gouki Minegishi, Go Nagahara, Yuta Oshima, Masahiro Suzuki, Shohei Taniguchi
Pages: 72438-72474 (37 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)