Statistical Consistency and Regret Bounds for Ranking
116
Microsoft Research331 тыс
Следующее
12.08.16 – 1102:00:48Популярные
30 дней – 4133:15
Опубликовано 12 августа 2016, 2:12
Ranking problems arise in an increasing number of applications, including for example information retrieval, recommendation systems, computational biology, drug discovery, and a variety of industrial prioritization tasks. In recent years, there has been much interest in developing machine learning algorithms for ranking problems, and in understanding the statistical properties of such algorithms. This talk will start with a brief overview of some recent results on the statistical consistency properties of ranking algorithms. The second part of the talk will then present some new results on regret bounds for a popular setting of ranking known as 'bipartite' ranking.
Свежие видео
4 дня – 3 56213:50
8 дней – 2 64635:22
8 дней – 1 3520:55
9 дней – 1 1880:23
9 дней – 1 1030:56
9 дней – 6 0350:14Случайные видео
92 дня – 9960:53
180 дней – 2 4494:00
14.12.22 – 85 1563:21
12.04.22 – 218 3259:45
14.03.22 – 37 1370:25
29.08.13 – 1 504 14616:20
8 дней – 3 47022:46
8 дней – 122 29012:13
8 дней – 9 8379:29
9 дней – 88 8891:00
9 дней – 2126:35
9 дней – 990:42
9 дней – 3 2670:16
3 дня – 7891:02