@PublicationReference(title="Factorization Machines", author="Steffen Rendle", year=2010, type=Conference, publication="Proceedings of the 10th IEEE International Conference on Data Mining (ICDM)", url="http://www.inf.uni-konstanz.de/~rendle/pdf/Rendle2010FM.pdf")

Package gov.sandia.cognition.learning.algorithm.factor.machine

Provides factorization machine algorithms.

See: Description

Class Summary

Class	Description
AbstractFactorizationMachineLearner	An abstract class for learning FactorizationMachines.
FactorizationMachine	Implements a Factorization Machine.
FactorizationMachineAlternatingLeastSquares	Implements an Alternating Least Squares (ALS) algorithm for learning a Factorization Machine.
FactorizationMachineStochasticGradient	Implements a Stochastic Gradient Descent (SGD) algorithm for learning a Factorization Machine.

Package gov.sandia.cognition.learning.algorithm.factor.machine Description

Provides factorization machine algorithms. Factorization machines are a combination of linear and factorized (reduced-dimensionality) pair-wise interactions between variables. As such, they are a combination of methods typically used for machine learning (linear methods, support vector machines) with those also used for recommendation systems (matrix factorization). The typical use is with sparse input vectors to turn a matrix factorization problem into a standard machine learning problem with an input vector. They can also be extended to higher-order interactions besides pairwise, but those are the most common.

Since:

3.4.0

Author:

Justin Basilico

See Also:

FactorizationMachine