deploy: SimplexLab/TorchJD@eeb3d9f

Author: ValerianRey

latest/docs/aggregation/aligned_mtl/index.html

@@ -301,7 +301,7 @@ <h1>Aligned-MTL<a class="headerlink" href="#aligned-mtl" title="Link to this hea
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
-<li><p><strong>pref_vector</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The preference vector to use.  If not provided, defaults to
+<li><p><strong>pref_vector</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.11)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The preference vector to use.  If not provided, defaults to
 <span class="math notranslate nohighlight">\(\begin{bmatrix} \frac{1}{m} &amp; \dots &amp; \frac{1}{m} \end{bmatrix}^T \in \mathbb{R}^m\)</span>.</p></li>
 <li><p><strong>scale_mode</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Literal" title="(in Python v3.14)"><code class="xref py py-data docutils literal notranslate"><span class="pre">Literal</span></code></a>[<code class="docutils literal notranslate"><span class="pre">'min'</span></code>, <code class="docutils literal notranslate"><span class="pre">'median'</span></code>, <code class="docutils literal notranslate"><span class="pre">'rmse'</span></code>]</span>) – The scaling mode used to build the balance transformation. <code class="docutils literal notranslate"><span class="pre">&quot;min&quot;</span></code> uses
 the smallest eigenvalue (default), <code class="docutils literal notranslate"><span class="pre">&quot;median&quot;</span></code> uses the median eigenvalue, and <code class="docutils literal notranslate"><span class="pre">&quot;rmse&quot;</span></code>
@@ -324,7 +324,7 @@ <h1>Aligned-MTL<a class="headerlink" href="#aligned-mtl" title="Link to this hea
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
-<li><p><strong>pref_vector</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The preference vector to use. If not provided, defaults to
+<li><p><strong>pref_vector</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.11)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The preference vector to use. If not provided, defaults to
 <span class="math notranslate nohighlight">\(\begin{bmatrix} \frac{1}{m} &amp; \dots &amp; \frac{1}{m} \end{bmatrix}^T \in \mathbb{R}^m\)</span>.</p></li>
 <li><p><strong>scale_mode</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Literal" title="(in Python v3.14)"><code class="xref py py-data docutils literal notranslate"><span class="pre">Literal</span></code></a>[<code class="docutils literal notranslate"><span class="pre">'min'</span></code>, <code class="docutils literal notranslate"><span class="pre">'median'</span></code>, <code class="docutils literal notranslate"><span class="pre">'rmse'</span></code>]</span>) – The scaling mode used to build the balance transformation. <code class="docutils literal notranslate"><span class="pre">&quot;min&quot;</span></code> uses
 the smallest eigenvalue (default), <code class="docutils literal notranslate"><span class="pre">&quot;median&quot;</span></code> uses the median eigenvalue, and <code class="docutils literal notranslate"><span class="pre">&quot;rmse&quot;</span></code>

latest/docs/aggregation/config/index.html

@@ -300,7 +300,7 @@ <h1>ConFIG<a class="headerlink" href="#config" title="Link to this heading">¶</
 Towards Conflict-free Training of Physics Informed Neural Networks</a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
-<dd class="field-odd"><p><strong>pref_vector</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The preference vector used to weight the rows. If not provided, defaults to
+<dd class="field-odd"><p><strong>pref_vector</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.11)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The preference vector used to weight the rows. If not provided, defaults to
 equal weights of 1.</p>
 </dd>
 </dl>

latest/docs/aggregation/constant/index.html

@@ -300,7 +300,7 @@ <h1>Constant<a class="headerlink" href="#constant" title="Link to this heading">
 the rows of the provided matrix, with constant, pre-determined weights.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
-<dd class="field-odd"><p><strong>weights</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a></span>) – The weights associated to the rows of the input matrices.</p>
+<dd class="field-odd"><p><strong>weights</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.11)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a></span>) – The weights associated to the rows of the input matrices.</p>
 </dd>
 </dl>
 </dd></dl>
@@ -312,7 +312,7 @@ <h1>Constant<a class="headerlink" href="#constant" title="Link to this heading">
 weights.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
-<dd class="field-odd"><p><strong>weights</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a></span>) – The weights to return at each call.</p>
+<dd class="field-odd"><p><strong>weights</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.11)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a></span>) – The weights to return at each call.</p>
 </dd>
 </dl>
 </dd></dl>

latest/docs/aggregation/dualproj/index.html

@@ -302,7 +302,7 @@ <h1>DualProj<a class="headerlink" href="#dualproj" title="Link to this heading">
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
-<li><p><strong>pref_vector</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The preference vector used to combine the rows. If not provided, defaults to
+<li><p><strong>pref_vector</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.11)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The preference vector used to combine the rows. If not provided, defaults to
 <span class="math notranslate nohighlight">\(\begin{bmatrix} \frac{1}{m} &amp; \dots &amp; \frac{1}{m} \end{bmatrix}^T \in \mathbb{R}^m\)</span>.</p></li>
 <li><p><strong>norm_eps</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">float</span></code></a></span>) – A small value to avoid division by zero when normalizing.</p></li>
 <li><p><strong>reg_eps</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">float</span></code></a></span>) – A small value to add to the diagonal of the gramian of the matrix. Due to
@@ -323,7 +323,7 @@ <h1>DualProj<a class="headerlink" href="#dualproj" title="Link to this heading">
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
-<li><p><strong>pref_vector</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The preference vector to use. If not provided, defaults to
+<li><p><strong>pref_vector</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.11)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The preference vector to use. If not provided, defaults to
 <span class="math notranslate nohighlight">\(\begin{bmatrix} \frac{1}{m} &amp; \dots &amp; \frac{1}{m} \end{bmatrix}^T \in \mathbb{R}^m\)</span>.</p></li>
 <li><p><strong>norm_eps</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">float</span></code></a></span>) – A small value to avoid division by zero when normalizing.</p></li>
 <li><p><strong>reg_eps</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">float</span></code></a></span>) – A small value to add to the diagonal of the gramian of the matrix. Due to

latest/docs/aggregation/graddrop/index.html

@@ -304,7 +304,7 @@ <h1>GradDrop<a class="headerlink" href="#graddrop" title="Link to this heading">
 <dd class="field-odd"><ul class="simple">
 <li><p><strong>f</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/collections.abc.html#collections.abc.Callable" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Callable</span></code></a></span>) – The function to apply to the Gradient Positive Sign Purity. It should be monotically
 increasing. Defaults to identity.</p></li>
-<li><p><strong>leak</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The tensor of leak values, determining how much each row is allowed to leak
+<li><p><strong>leak</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.11)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The tensor of leak values, determining how much each row is allowed to leak
 through. Defaults to None, which means no leak.</p></li>
 </ul>
 </dd>

latest/docs/aggregation/upgrad/index.html

@@ -302,7 +302,7 @@ <h1>UPGrad<a class="headerlink" href="#upgrad" title="Link to this heading">¶</
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
-<li><p><strong>pref_vector</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The preference vector used to combine the projected rows.  If not provided,
+<li><p><strong>pref_vector</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.11)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The preference vector used to combine the projected rows.  If not provided,
 defaults to <span class="math notranslate nohighlight">\(\begin{bmatrix} \frac{1}{m} &amp; \dots &amp; \frac{1}{m} \end{bmatrix}^T \in
 \mathbb{R}^m\)</span>.</p></li>
 <li><p><strong>norm_eps</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">float</span></code></a></span>) – A small value to avoid division by zero when normalizing.</p></li>
@@ -324,7 +324,7 @@ <h1>UPGrad<a class="headerlink" href="#upgrad" title="Link to this heading">¶</
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
-<li><p><strong>pref_vector</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.10)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The preference vector to use. If not provided, defaults to
+<li><p><strong>pref_vector</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.11)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – The preference vector to use. If not provided, defaults to
 <span class="math notranslate nohighlight">\(\begin{bmatrix} \frac{1}{m} &amp; \dots &amp; \frac{1}{m} \end{bmatrix}^T \in \mathbb{R}^m\)</span>.</p></li>
 <li><p><strong>norm_eps</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">float</span></code></a></span>) – A small value to avoid division by zero when normalizing.</p></li>
 <li><p><strong>reg_eps</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">float</span></code></a></span>) – A small value to add to the diagonal of the gramian of the matrix. Due to