|
ИСТИНА |
Войти в систему Регистрация |
ИСТИНА ФИЦ ПХФ и МХ РАН |
||
Learning Supervised PageRank with Gradient-Based and Gradient-Free Optimization Methodsдоклад на конференции
- Авторы: Lev Bogolubsky, Pavel Dvurechensky, Alexander Gasnikov, Maksim Zhukovskii, Yurii Nesterov, Andrei Raigorodskii, Aleksey Tikhonov, Gleb Gusev
- Международная Конференция : NIPS 2016
- Даты проведения конференции: 5-10 декабря 2016
- Дата доклада: 5 декабря 2016
- Тип доклада: Стендовый
- Докладчик: не указан
- Место проведения: Барселона, Испания
-
Аннотация доклада:
In this paper, we consider a non-convex loss-minimization problem of learning Supervised PageRank models, which can account for features of nodes and edges. We propose gradient-based and random gradient-free methods to solve this problem. Our algorithms are based on the concept of an inexact oracle and unlike the state-ofthe-art gradient-based method we manage to provide theoretically the convergence rate guarantees for both of them. Finally, we compare the performance of the proposed optimization methods with the state of the art applied to a ranking task.
- Добавил в систему: Боголюбский Лев Игоревич