deploy: SimplexLab/TorchJD@aa87f95

Author: ValerianRey

latest/docs/aggregation/aligned_mtl/index.html

@@ -241,7 +241,7 @@
 <span id="aligned-mtl"></span><h1>Aligned-MTL<a class="headerlink" href="#module-torchjd.aggregation.aligned_mtl" title="Link to this heading">¶</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torchjd.aggregation.aligned_mtl.AlignedMTL">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torchjd.aggregation.aligned_mtl.</span></span><span class="sig-name descname"><span class="pre">AlignedMTL</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pref_vector</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/TorchJD/torchjd/blob/main/src/torchjd/aggregation/aligned_mtl.py#L36-L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchjd.aggregation.aligned_mtl.AlignedMTL" title="Link to this definition">¶</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torchjd.aggregation.aligned_mtl.</span></span><span class="sig-name descname"><span class="pre">AlignedMTL</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pref_vector</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/TorchJD/torchjd/blob/main/src/torchjd/aggregation/aligned_mtl.py#L37-L74"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchjd.aggregation.aligned_mtl.AlignedMTL" title="Link to this definition">¶</a></dt>
 <dd><p><a class="reference internal" href="../bases/#torchjd.aggregation.bases.Aggregator" title="torchjd.aggregation.bases.Aggregator"><code class="xref py py-class docutils literal notranslate"><span class="pre">Aggregator</span></code></a> as defined in Algorithm 1 of
 <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">

latest/docs/aggregation/imtl_g/index.html

@@ -241,7 +241,7 @@
 <span id="imtl-g"></span><h1>IMTL-G<a class="headerlink" href="#module-torchjd.aggregation.imtl_g" title="Link to this heading">¶</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torchjd.aggregation.imtl_g.IMTLG">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torchjd.aggregation.imtl_g.</span></span><span class="sig-name descname"><span class="pre">IMTLG</span></span><a class="reference external" href="https://github.com/TorchJD/torchjd/blob/main/src/torchjd/aggregation/imtl_g.py#L7-L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchjd.aggregation.imtl_g.IMTLG" title="Link to this definition">¶</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torchjd.aggregation.imtl_g.</span></span><span class="sig-name descname"><span class="pre">IMTLG</span></span><a class="reference external" href="https://github.com/TorchJD/torchjd/blob/main/src/torchjd/aggregation/imtl_g.py#L8-L31"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchjd.aggregation.imtl_g.IMTLG" title="Link to this definition">¶</a></dt>
 <dd><p><a class="reference internal" href="../bases/#torchjd.aggregation.bases.Aggregator" title="torchjd.aggregation.bases.Aggregator"><code class="xref py py-class docutils literal notranslate"><span class="pre">Aggregator</span></code></a> generalizing the method described in
 <a class="reference external" href="https://discovery.ucl.ac.uk/id/eprint/10120667/">Towards Impartial Multi-task Learning</a>.
 This generalization, defined formally in <a class="reference external" href="https://arxiv.org/pdf/2406.16232">Jacobian Descent For Multi-Objective Optimization</a>, supports matrices with some linearly dependant rows.</p>

latest/docs/aggregation/krum/index.html

@@ -241,7 +241,7 @@
 <span id="krum"></span><h1>Krum<a class="headerlink" href="#module-torchjd.aggregation.krum" title="Link to this heading">¶</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torchjd.aggregation.krum.Krum">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torchjd.aggregation.krum.</span></span><span class="sig-name descname"><span class="pre">Krum</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_byzantine</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_selected</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/TorchJD/torchjd/blob/main/src/torchjd/aggregation/krum.py#L8-L49"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchjd.aggregation.krum.Krum" title="Link to this definition">¶</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torchjd.aggregation.krum.</span></span><span class="sig-name descname"><span class="pre">Krum</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_byzantine</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_selected</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/TorchJD/torchjd/blob/main/src/torchjd/aggregation/krum.py#L9-L50"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchjd.aggregation.krum.Krum" title="Link to this definition">¶</a></dt>
 <dd><p><a class="reference internal" href="../bases/#torchjd.aggregation.bases.Aggregator" title="torchjd.aggregation.bases.Aggregator"><code class="xref py py-class docutils literal notranslate"><span class="pre">Aggregator</span></code></a> for adversarial federated learning, as defined
 in <a class="reference external" href="https://proceedings.neurips.cc/paper/2017/file/f4b9ec30ad9f68f89b29639786cb62ef-Paper.pdf">Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent</a>.</p>
 <dl class="field-list simple">

latest/docs/aggregation/pcgrad/index.html

@@ -241,7 +241,7 @@
 <span id="pcgrad"></span><h1>PCGrad<a class="headerlink" href="#module-torchjd.aggregation.pcgrad" title="Link to this heading">¶</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torchjd.aggregation.pcgrad.PCGrad">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torchjd.aggregation.pcgrad.</span></span><span class="sig-name descname"><span class="pre">PCGrad</span></span><a class="reference external" href="https://github.com/TorchJD/torchjd/blob/main/src/torchjd/aggregation/pcgrad.py#L7-L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchjd.aggregation.pcgrad.PCGrad" title="Link to this definition">¶</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torchjd.aggregation.pcgrad.</span></span><span class="sig-name descname"><span class="pre">PCGrad</span></span><a class="reference external" href="https://github.com/TorchJD/torchjd/blob/main/src/torchjd/aggregation/pcgrad.py#L8-L29"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchjd.aggregation.pcgrad.PCGrad" title="Link to this definition">¶</a></dt>
 <dd><p><a class="reference internal" href="../bases/#torchjd.aggregation.bases.Aggregator" title="torchjd.aggregation.bases.Aggregator"><code class="xref py py-class docutils literal notranslate"><span class="pre">Aggregator</span></code></a> as defined in algorithm 1 of
 <a class="reference external" href="https://arxiv.org/pdf/2001.06782.pdf">Gradient Surgery for Multi-Task Learning</a>.</p>
 <div class="admonition-example admonition">