Gradient Descent

Manopt.stochastic_gradient_descentFunction
stochastic_gradient_descent(M, ∇F, x)

perform a stochastic gradient descent

Input

  • M a manifold $\mathcal M$
  • ∇F – a gradient function, that either returns a vector of the subgradients or is a vector of gradients
  • x – an initial value $x ∈ \mathcal M$

Optional

  • cost – (missing) you can provide a cost function for example to track the function value
  • evaluation_order – (:Random) – whether to use a randomly permuted sequence (:FixedRandom), a per cycle permuted sequence (:Linear) or the default :Random one.
  • stopping_criterion (StopAfterIteration(1000))– a StoppingCriterion
  • stepsize (ConstantStepsize(1.0)) a Stepsize
  • order_type (:RandomOder) a type of ordering of gradient evaluations. values are :RandomOrder, a :FixedPermutation, :LinearOrder
  • order - ([1:n]) the initial permutation, where n is the number of gradients in ∇F.
  • retraction_method – (ExponentialRetraction()) a retraction(M,x,ξ) to use.

Output

  • x_opt – the resulting (approximately critical) point of gradientDescent

OR

  • options - the options returned by the solver (see return_options)
source

Options

Manopt.StochasticGradientDescentOptionsType
StochasticGradientDescentOptions <: AbstractStochasticGradientDescentOptions

Store the following fields for a default stochastic gradient descent algorithm, see also StochasticGradientProblem and stochastic_gradient_descent.

fields

Fields

  • x the current iterate
  • stopping_criterion (StopAfterIteration(1000))– a StoppingCriterion
  • stepsize (ConstantStepsize(1.0)) a Stepsize
  • evaluation_order – (:Random) – whether to use a randomly permuted sequence (:FixedRandom), a per cycle permuted sequence (:Linear) or the default :Random one.
  • order the current permutation
  • retraction_method – (ExponentialRetraction()) a retraction(M,x,ξ) to use.

Constructor

StochasticGradientDescentOptions(x)

Create a StochasticGradientDescentOptions with start point x. all other fields are optional keyword arguments.

source

Additionally, the options share a DirectionUpdateRule, so you can also apply MomentumGradient and AverageGradient here. The most inner one should always be.

Manopt.StochasticGradientType
StochasticGradient <: DirectionUpdateRule

The default gradient processor, which just evaluates the (stochastic) gradient or a subset thereof.

source