On Gradient-Based Optimization: Accelerated, Stochastic and Nonconvex
5 535
21.7
Microsoft Research320 тыс
Следующее
29.05.18 – 1 92047:43Популярные
148 дней – 60810:32
03.11.22 – 7581:00:39Опубликовано 29 мая 2018, 3:18
Many new theoretical challenges have arisen in the area of gradient-based optimization for large-scale statistical data analysis, driven by the needs of applications and the opportunities provided by new hardware and software platforms. I discuss several recent, related results in this area: (1) a new framework for understanding Nesterov acceleration, obtained by taking a continuous-time, Lagrangian/Hamiltonian/symplectic perspective, (2) a discussion of how to escape saddle points efficiently in nonconvex optimization, and (3) the acceleration of Langevin diffusion.
See more at microsoft.com/en-us/research/v...
See more at microsoft.com/en-us/research/v...
Свежие видео
7 дней – 4600:35
8 дней – 3310:42
9 дней – 102 58712:32
9 дней – 821:21
12 дней – 7 6890:31Случайные видео
137 дней – 5 9690:18
13.09.22 – 288 7809:50
17.07.22 – 2 022 88111:40
16.01.22 – 9832:49
19.07.21 – 3 4055:37
31.10.07 – 5 2285:27
1 день – 6 4759:51
1 день – 18 1196:09
2 дня – 1 1980:44
3 дня – 100 14613:03
6 дней – 3817:55
6 дней – 9 4300:17
3 дня – 1 5530:58