Package linear_operators :: Package iterative :: Module criterions :: Class Criterion

Class Criterion

object --+
         |
        Criterion

Known Subclasses:


A class representing criterions such as :
..math: || y - H x ||^2 + sum_i \hypers_i || D_i x ||^2

Parameters
----------

H : LinearOperator
    Model.
y : ndarray
    Data array.
hypers: tuple or array
    Hypeparameter of each prior.
Ds : tuple of LinearOperators
    Prior models.
norms : tuple
    Can be norm2, huber, normp
store : boolean (default: True)
    Store last criterion computation.

Returns
-------

Returns an Criterion instance with __call__ and gradient methods.

Instance Methods

[hide private]

__init__(self, model, data, hypers=[], priors=[], norms=[], store=True)
x.__init__(...) initializes x; see help(type(x)) for signature source code

islast(self, x)

source code

load_last(self)

source code

get_residuals(self, x)

source code

save(self, x, Hx, r, rd)

source code

__call__(self, x)

source code

gradient(self, x)
First order derivative of the criterion as a function of x.

source code

Inherited from object: __delattr__, __format__, __getattribute__, __hash__, __new__, __reduce__, __reduce_ex__, __repr__, __setattr__, __sizeof__, __str__, __subclasshook__

Properties

[hide private]

Inherited from object: __class__

Method Details

[hide private]

init(self, model, data, hypers=`[]`, priors=`[]`, norms=`[]`, store=True)
(Constructor)

source code

x.__init__(...) initializes x; see help(type(x)) for signature

Overrides: object.__init__: (inherited documentation)

Class Criterion

__init__(self, model, data, hypers=[], priors=[], norms=[], store=True) (Constructor)

init(self, model, data, hypers=`[]`, priors=`[]`, norms=`[]`, store=True)
(Constructor)