TY - JOUR
T1 - Sgdlibrary
T2 - A matlab library for stochastic optimization algorithms
AU - Kasai, Hiroyuki
PY - 2018/4/1
Y1 - 2018/4/1
N2 - We consider the problem of finding the minimizer of a function f : Rd → R of the finite-sum form min f(w) = 1/nn i fi(w). This problem has been studied intensively in recent years in the field of machine learning (ML). One promising approach for large-scale data is to use a stochastic optimization algorithm to solve the problem. SGDLibrary is a readable, flexible and extensible pure-MATLAB library of a collection of stochastic optimization algorithms. The purpose of the library is to provide researchers and implementers a comprehensive evaluation environment for the use of these algorithms on various ML problems.
AB - We consider the problem of finding the minimizer of a function f : Rd → R of the finite-sum form min f(w) = 1/nn i fi(w). This problem has been studied intensively in recent years in the field of machine learning (ML). One promising approach for large-scale data is to use a stochastic optimization algorithm to solve the problem. SGDLibrary is a readable, flexible and extensible pure-MATLAB library of a collection of stochastic optimization algorithms. The purpose of the library is to provide researchers and implementers a comprehensive evaluation environment for the use of these algorithms on various ML problems.
KW - Finite-sum minimization problem
KW - Large-scale optimization problem
KW - Stochastic gradient
KW - Stochastic optimization
UR - http://www.scopus.com/inward/record.url?scp=85048927233&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048927233&partnerID=8YFLogxK
M3 - Article
AN - SCOPUS:85048927233
VL - 18
SP - 1
EP - 5
JO - Journal of Machine Learning Research
JF - Journal of Machine Learning Research
SN - 1532-4435
ER -