Safe Haskell	None

Numeric.SGD

Description

Stochastic gradient descent implementation using mutable vectors for efficient update of the parameters vector. A user is provided with the immutable version of parameters vector so he is able to compute the gradient outside the IO/ST monad. Currently only the Gaussian priors are implemented.

This is a preliminary version of the SGD library and API may change in future versions.

Synopsis

Documentation

data SgdArgs Source

SGD parameters controlling the learning process.

Constructors

SgdArgs
Fields batchSize :: Int Size of the batch regVar :: Double Regularization variance iterNum :: Double Number of iterations gain0 :: Double Initial gain parameter tau :: Double After how many iterations over the entire dataset the gain parameter is halved

sgdArgsDefault :: SgdArgs Source

Default SGD parameter values.

type Dataset x = Vector xSource

Dataset with elements of x type.

type Para = Vector Double Source

Vector of parameters.

sgd Source

Arguments

:: SgdArgs	SGD parameter values
-> (Para -> x -> Grad)	Gradient for dataset element
-> Dataset x	Dataset
-> Para	Starting point
-> Para	SGD result

Pure version of the stochastic gradient descent method.

sgdM Source

Arguments

:: PrimMonad m
=> SgdArgs	SGD parameter values
-> (Para -> Int -> m ())	Notification run every update
-> (Para -> x -> Grad)	Gradient for dataset element
-> Dataset x	Dataset
-> Para	Starting point
-> m Para	SGD result

Monadic version of the stochastic gradient descent method. A notification function can be used to provide user with information about the progress of the learning.

module Numeric.SGD.Grad