Learning Supervised PageRank with Gradient-Based and Gradient-Free Optimization Methods

被引：0

作者：

Bogolubsky, Lev ^{[1
,2
]}

Gusev, Gleb ^{[1
,6
]}

Raigorodskii, Andrei ^{[1
,2
,3
,6
]}

Tikhonov, Aleksey ^{[1
]}

Zhukovskii, Maksim ^{[1
,6
]}

Dvurechensky, Pavel ^{[4
,5
]}

Gasnikov, Alexander ^{[5
,6
]}

Nesterov, Yurii ^{[7
,8
]}

机构：

[1] Yandex, Moscow, Russia

[2] Moscow MV Lomonosov State Univ, Moscow, Russia

[3] Buryat State Univ, Ulan Ude, Russia

[4] Weierstrass Inst, Berlin, Germany

[5] Inst Informat Transmiss Problems RAS, Moscow, Russia

[6] Moscow Inst Phys & Technol, Moscow, Russia

[7] Ctr Operat Res & Econometr, Louvain La Neuve, Belgium

[8] Higher Sch Econ, Moscow, Russia

来源：

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016) | 2016年 / 29卷

基金：

俄罗斯科学基金会;

关键词：

DERIVATIVES;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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-of-the-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.

引用

页数：9

共 50 条

[21] Intractability of Learning the Discrete Logarithm with Gradient-Based Methods
Takhanov, Rustem
Tezekbayev, Maxat
Pak, Artur
Bolatov, Arman
Kadyrsizova, Zhibek
Assylbekov, Zhenisbek
ASIAN CONFERENCE ON MACHINE LEARNING, VOL 222, 2023, 222
[22] Gradient-based optimization of hyperparameters
Bengio, Y
NEURAL COMPUTATION, 2000, 12 (08) : 1889 - 1900
[23] Gradient-based simulation optimization
Kim, Sujin
PROCEEDINGS OF THE 2006 WINTER SIMULATION CONFERENCE, VOLS 1-5, 2006, : 159 - 167
[24] Accelerated Gradient-Free Optimization Methods with a Non-Euclidean Proximal Operator
Vorontsova, E. A.
Gasnikov, A. V.
Gorbunov, E. A.
Dvurechenskii, P. E.
AUTOMATION AND REMOTE CONTROL, 2019, 80 (08) : 1487 - 1501
[25] Multi-objective topology optimisation for acoustic porous materials using gradient-based, gradient-free, and hybrid strategies
Ramamoorthy, Vivek T.
Ozcan, Ender
Parkes, Andrew J.
Jaouen, Luc
Becot, Francois-Xavier
JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2023, 153 (05): : 2945 - 2955
[26] Asynchronous Gossip-Based Gradient-Free Method for Multiagent Optimization
Yuan, Deming
ABSTRACT AND APPLIED ANALYSIS, 2014,
[27] Accelerated Gradient-Free Optimization Methods with a Non-Euclidean Proximal Operator
E. A. Vorontsova
A. V. Gasnikov
E. A. Gorbunov
P. E. Dvurechenskii
Automation and Remote Control, 2019, 80 : 1487 - 1501
[28] Training Fuzzy Cognitive Maps Using Gradient-Based Supervised Learning
Gregor, Michal
Groumpos, Peter P.
ARTIFICIAL INTELLIGENCE APPLICATIONS AND INNOVATIONS, AIAI 2013, 2013, 412 : 547 - 556
[29] CHARACTERIZATION OF TRAINING ERRORS IN SUPERVISED LEARNING USING GRADIENT-BASED RULES
WANG, J
MALAKOOTI, B
NEURAL NETWORKS, 1993, 6 (08) : 1073 - 1087
[30] Gradient-free strategies to robust well control optimization
Pinto, Jefferson Wellano Oliveira
Tueros, Juan Alberto Rojas
Horowitz, Bernardo
da Silva, Silvana Maria Bastos Afonso
Willmersdorf, Ramiro Brito
de Oliveira, Diego Felipe Barbosa
COMPUTATIONAL GEOSCIENCES, 2020, 24 (06) : 1959 - 1978

← 1 2 3 4 5 →