get_gradient_formula

Generate formula and input args list for the Gradient of an existing formula

internal

The 'KeOps' library lets you compute generic reductions of
very large arrays whose entries are given by a mathematical formula
with CPU and GPU computing support. It combines a tiled reduction
scheme with an automatic differentiation engine. It is perfectly
suited to the efficient computation of Kernel dot products and the
associated gradients, even when the full kernel matrix does not fit
into the GPU memory.

Ghislain Durif

rkeops

Kernel Operations on GPU or CPU, with Autodiff, without Memory
Overflows

Amelie Vernay

Chloe Serre-Combe

Benjamin Charlier

Jean Feydy

Joan A. Glaunès

François-David Collin

get_gradient_formula function

<dl><dt>formula</dt>
<dd>text string, an operator formula (see Details).</dd>
<dt>args</dt>
<dd>vector of text string, formula arguments (see Details).</dd>
<dt>var</dt>
<dd>a text string or an integer number indicating regarding to which
variable/parameter (given by name or by position starting at 0) the
gradient of the formula should be computed.</dd>
<dt>args_info</dt>
<dd>list, internal (output of
<code>rkeops:::parse_args(formula,args)</code>)</dd></dl>

Arguments

Author

Generate formula and input args list for the Gradient of an existing formula — get_gradient_formula

<dl>

<dt>formula</dt>
<dd>text string, an operator formula (see Details).</dd>


<dt>args</dt>
<dd>vector of text string, formula arguments (see Details).</dd>


<dt>var</dt>
<dd>a text string or an integer number indicating regarding to which
variable/parameter (given by name or by position starting at 0) the
gradient of the formula should be computed.</dd>


<dt>args_info</dt>
<dd>list, internal (output of
<code>rkeops:::parse_args(formula,args)</code>)</dd>

</dl>

Generate formula and input args list for the Gradient of an existing formula

get_gradient_formula: Generate formula and input args list for the Gradient of an existing formula

Description

Usage

Value

Arguments

Author