vaeac_get_evaluation_criteria

Extract the Training VLB and Validation IWAE from a list of explanations objects using the vaeac approach

internal

Complex machine learning models are often hard to interpret. However, in
many situations it is crucial to understand and explain why a model made a specific
prediction. Shapley values is the only method for such prediction explanation framework
with a solid theoretical foundation. Previously known methods for estimating the Shapley
values do, however, assume feature independence. This package implements methods which accounts for any feature
dependence, and thereby produces more accurate estimates of the true Shapley values.
An accompanying 'Python' wrapper ('shaprpy') is available through the GitHub repository.

Martin Jullum

shapr

Prediction Explanation with Dependence-Aware Shapley Values

Lars Henry Berge Olsen

Annabelle Redelmeier

Jon Lachmann

Nikolai Sellereite

Anders Løland

Jens Christian Wahl

Camilla Lingjærde

Norsk Regnesentral 

vaeac_get_evaluation_criteria function

<dl><dt>explanation_list</dt>
<dd>A list of <code>explain()</code> objects applied to the same data, model, and
<code>vaeac</code> must be the used approach. If the entries in the list is named, then the function use
these names. Otherwise, it defaults to the approach names (with integer suffix for duplicates)
for the explanation objects in <code>explanation_list</code>.</dd></dl>

Arguments

Author

Extract the Training VLB and Validation IWAE from a list of explanations objects using the vaeac approach — vaeac_get_evaluation_criteria

<dl>

<dt>explanation_list</dt>
<dd>A list of <code>explain()</code> objects applied to the same data, model, and
<code>vaeac</code> must be the used approach. If the entries in the list is named, then the function use
these names. Otherwise, it defaults to the approach names (with integer suffix for duplicates)
for the explanation objects in <code>explanation_list</code>.</dd>

</dl>

Extract the Training VLB and Validation IWAE from a list of explanations objects using the vaeac approach

vaeac_get_evaluation_criteria: Extract the Training VLB and Validation IWAE from a list of explanations objects using the vaeac approach

Description

Usage

Value

Arguments

Author