Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Bok, Jinho"'
Autor:
Bok, Jinho, Altschuler, Jason M.
Surprisingly, recent work has shown that gradient descent can be accelerated without using momentum -- just by judiciously choosing stepsizes. An open question raised by several papers is whether this phenomenon of stepsize-based acceleration holds m
Externí odkaz:
http://arxiv.org/abs/2412.05497
Noisy gradient descent and its variants are the predominant algorithms for differentially private machine learning. It is a fundamental question to quantify their privacy leakage, yet tight characterizations remain open even in the foundational setti
Externí odkaz:
http://arxiv.org/abs/2403.00278
Autor:
ALTSCHULER, JASON M.1 alts@upenn.edu, BOK, JINHO1 jinhobok@upenn.edu, TALWAR, KUNAL2 ktalwar@apple.com
Publikováno v:
SIAM Journal on Computing. 2024, Vol. 53 Issue 4, p969-1001. 33p.
