Fast Algorithms for Online Stochastic Convex Programming
437
72.8
Microsoft Research332 тыс
Следующее
Популярные
228 дней – 12 9445:06
Опубликовано 22 июня 2016, 0:25
We introduce the Online Stochastic Convex Programming (CP) problem, a very general version of stochastic online problems which allows arbitrary convex objectives and feasibility constraints. This problem generalizes the well-studied online stochastic packing problem. We present fast algorithms for these problems, which achieve near-optimal guarantees for the i.i.d. and the random permutation models of stochastic inputs. When applied to the special case of online packing, our ideas yield a simpler and faster primal-dual algorithm which achieves the optimal competitive ratio. We make explicit the connection between the primal-dual paradigm, online learning algorithms and the online stochastic packing problem. Joint work with Shipra Agrawal
Свежие видео
3 дня – 79 8075:37
3 дня – 8 8941:41
11 дней – 1 3960:59
11 дней – 5450:19
Случайные видео
75 дней – 855:14
228 дней – 594 7700:41
330 дней – 41 8073:10
24.01.23 – 1 7153:34
19.08.22 – 1872:04
03.02.13 – 95 3503:29
1 день – 9 6180:16
4 дня – 22 8553:36
5 дней – 3 10311:16
15 дней – 41812:09
15 дней – 7160:15
15 дней – 2021:24
16 дней – 3 5939:27
1 день – 80 44513:31