On Gradient-Based Optimization: Accelerated, Stochastic and Nonconvex
5 705
21.1
Microsoft Research334 тыс
Следующее
29.05.18 – 1 94447:43Популярные
354 дня – 24427:12
12.12.22 – 63028:53Опубликовано 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
4 дня – 4 6192:08
8 дней – 011:59
16 дней – 11 2371:02
17 дней – 9010:13
19 дней – 6 2770:26
23 дня – 50 5860:22Случайные видео
16 дней – 22 2172:30
104 дня – 895:14
346 дней – 1 332 7300:11
22.08.21 – 368 6007:52
21.05.21 – 4 311 22814:21
01.03.11 – 171 2050:35
1 день – 17 48813:10
3 дня – 5 2261:00
3 дня – 2950:29
3 дня – 1 9490:54
4 дня – 890:27
3 дня – 1 3571:03