adaptive_imputation

<code>adaptive_imputation</code> objects are a subclass of
<code>LRMF3::svd_like()</code>, with an additional field <code>alpha</code>.

Implements the AdaptiveImpute matrix completion
algorithm of 'Intelligent Initialization and Adaptive Thresholding for
Iterative Matrix Completion',
<https://amstat.tandfonline.com/doi/abs/10.1080/10618600.2018.1518238>.
AdaptiveImpute is useful for embedding sparsely observed matrices,
often out performs competing matrix completion algorithms, and
self-tunes its hyperparameter, making usage easy.

Alex Hayes

fastadi

Self-Tuning Data Adaptive Matrix Imputation

Juhee Cho

Donggyu Kim

Karl Rohe

adaptive_imputation function

<dl><dt>u</dt>
<dd>A matrix "left singular-ish" vectors.</dd>
<dt>d</dt>
<dd>A vector of "singular-ish" values.</dd>
<dt>v</dt>
<dd>A matrix of "right singular-ish" vectors.</dd>
<dt>alpha</dt>
<dd>Value of <code>alpha</code> after final iteration.</dd>
<dt>...</dt>
<dd>Optional additional items to pass to the constructor.</dd></dl>

Arguments

Create an Adaptive Imputation object — adaptive_imputation

<dl>

<dt>u</dt>
<dd>A matrix "left singular-ish" vectors.</dd>


<dt>d</dt>
<dd>A vector of "singular-ish" values.</dd>


<dt>v</dt>
<dd>A matrix of "right singular-ish" vectors.</dd>


<dt>alpha</dt>
<dd>Value of <code>alpha</code> after final iteration.</dd>


<dt>...</dt>
<dd>Optional additional items to pass to the constructor.</dd>

</dl>

adaptive_imputation: Create an Adaptive Imputation object

Description

Usage

Value

Arguments