deploy: SimplexLab/TorchJD@711e778

Author: ValerianRey

latest/docs/aggregation/aligned_mtl/index.html

@@ -299,7 +299,7 @@ <h1>Aligned-MTL<a class="headerlink" href="#aligned-mtl" title="Link to this hea
 <a class="reference external" href="https://openaccess.thecvf.com/content/CVPR2023/papers/Senushkin_Independent_Component_Alignment_for_Multi-Task_Learning_CVPR_2023_paper.pdf">Independent Component Alignment for Multi-Task Learning</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 v2.9)"><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
+<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 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>
 </dd>
 </dl>
@@ -316,7 +316,7 @@ <h1>Aligned-MTL<a class="headerlink" href="#aligned-mtl" title="Link to this hea
 <a class="reference internal" href="#torchjd.aggregation.AlignedMTL" title="torchjd.aggregation.AlignedMTL"><code class="xref py py-class docutils literal notranslate"><span class="pre">AlignedMTL</span></code></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 v2.9)"><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
+<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 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>
 </dd>
 </dl>

latest/docs/aggregation/config/index.html

@@ -299,7 +299,7 @@ <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 v2.9)"><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 v2.10)"><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
 equal weights of 1.</p>
 </dd>
 </dl>

latest/docs/aggregation/constant/index.html

@@ -299,7 +299,7 @@ <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 v2.9)"><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 v2.10)"><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>
 </dl>
 </dd></dl>
@@ -311,7 +311,7 @@ <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 v2.9)"><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 v2.10)"><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>
 </dl>
 </dd></dl>

latest/docs/aggregation/dualproj/index.html

@@ -301,7 +301,7 @@ <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 v2.9)"><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 v2.10)"><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
 <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
@@ -322,7 +322,7 @@ <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 v2.9)"><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 v2.10)"><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
 <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/flattening/index.html

@@ -305,7 +305,7 @@ <h1>Flattening<a class="headerlink" href="#flattening" title="Link to this headi
 <code class="docutils literal notranslate"><span class="pre">[2,</span> <span class="pre">3]</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
-<dd class="field-odd"><p><strong>weighting</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference internal" href="../#torchjd.aggregation.Weighting" title="torchjd.aggregation._weighting_bases.Weighting"><code class="xref py py-class docutils literal notranslate"><span class="pre">Weighting</span></code></a>[<a class="reference external" href="https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.9)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a>]</span>) – The weighting to apply to the Gramian matrix.</p>
+<dd class="field-odd"><p><strong>weighting</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference internal" href="../#torchjd.aggregation.Weighting" title="torchjd.aggregation._weighting_bases.Weighting"><code class="xref py py-class docutils literal notranslate"><span class="pre">Weighting</span></code></a>[<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 weighting to apply to the Gramian matrix.</p>
 </dd>
 </dl>
 </dd></dl>

latest/docs/aggregation/graddrop/index.html

@@ -303,7 +303,7 @@ <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 v2.9)"><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 v2.10)"><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
 through. Defaults to None, which means no leak.</p></li>
 </ul>
 </dd>

latest/docs/aggregation/upgrad/index.html

@@ -301,7 +301,7 @@ <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 v2.9)"><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 v2.10)"><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,
 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>
@@ -323,7 +323,7 @@ <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 v2.9)"><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 v2.10)"><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
 <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