lsst.scarlet.lite gee10cc3b42+90ebb246c7
Loading...
Searching...
No Matches
Public Member Functions | Public Attributes | List of all members
lsst.scarlet.lite.parameters.AdaproxParameter Class Reference
Inheritance diagram for lsst.scarlet.lite.parameters.AdaproxParameter:
lsst.scarlet.lite.parameters.Parameter

Public Member Functions

 __init__ (self, np.ndarray x, Callable|float step, Callable|None grad=None, Callable|None prox=None, float b1=0.9, float b2=0.999, float eps=1e-8, float p=0.25, np.ndarray|None m0=None, np.ndarray|None v0=None, np.ndarray|None vhat0=None, str scheme="amsgrad", float prox_e_rel=1e-6)
 
 update (self, int it, np.ndarray input_grad, *args)
 
- Public Member Functions inherited from lsst.scarlet.lite.parameters.Parameter
float step (self)
 
tuple[int,...] shape (self)
 
npt.DTypeLike dtype (self)
 
Parameter copy (self)
 
 resize (self, Box old_box, Box new_box)
 

Public Attributes

 b1
 
 b2
 
 eps
 
 p
 
 phi_psi
 
 e_rel
 
 x
 
- Public Attributes inherited from lsst.scarlet.lite.parameters.Parameter
 x
 
 helpers
 
 grad
 
 prox
 

Additional Inherited Members

- Protected Attributes inherited from lsst.scarlet.lite.parameters.Parameter
 _step
 

Detailed Description

Operator updated using te Proximal ADAM algorithm

Uses multiple variants of adaptive quasi-Newton gradient descent
    * Adam (Kingma & Ba 2015)
    * NAdam (Dozat 2016)
    * AMSGrad (Reddi, Kale & Kumar 2018)
    * PAdam (Chen & Gu 2018)
    * AdamX (Phuong & Phong 2019)
    * RAdam (Liu et al. 2019)
See details of the algorithms in the respective papers.

Constructor & Destructor Documentation

◆ __init__()

lsst.scarlet.lite.parameters.AdaproxParameter.__init__ ( self,
np.ndarray x,
Callable | float step,
Callable | None grad = None,
Callable | None prox = None,
float b1 = 0.9,
float b2 = 0.999,
float eps = 1e-8,
float p = 0.25,
np.ndarray | None m0 = None,
np.ndarray | None v0 = None,
np.ndarray | None vhat0 = None,
str scheme = "amsgrad",
float prox_e_rel = 1e-6 )

Member Function Documentation

◆ update()

lsst.scarlet.lite.parameters.AdaproxParameter.update ( self,
int it,
np.ndarray input_grad,
* args )
Update the parameter and meta-parameters using the PGM

See `~Parameter` for more.

Reimplemented from lsst.scarlet.lite.parameters.Parameter.


The documentation for this class was generated from the following file: