deploy: SimplexLab/TorchJD@6d799a3

Author: ValerianRey

latest/docs/aggregation/constant/index.html

@@ -242,7 +242,7 @@
 <h1>Constant<a class="headerlink" href="#constant" title="Link to this heading">¶</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torchjd.aggregation.Constant">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torchjd.aggregation.</span></span><span class="sig-name descname"><span class="pre">Constant</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weights</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/TorchJD/torchjd/blob/main/src/torchjd/aggregation/_constant.py#L8-L38"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchjd.aggregation.Constant" 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.</span></span><span class="sig-name descname"><span class="pre">Constant</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weights</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/TorchJD/torchjd/blob/main/src/torchjd/aggregation/_constant.py#L8-L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchjd.aggregation.Constant" title="Link to this definition">¶</a></dt>
 <dd><p><a class="reference internal" href="../bases/#torchjd.aggregation.Aggregator" title="torchjd.aggregation._aggregator_bases.Aggregator"><code class="xref py py-class docutils literal notranslate"><span class="pre">Aggregator</span></code></a> that makes a linear combination of
 the rows of the provided matrix, with constant, pre-determined weights.</p>
 <dl class="field-list simple">

latest/docs/aggregation/mgda/index.html

@@ -242,7 +242,7 @@
 <h1>MGDA<a class="headerlink" href="#mgda" title="Link to this heading">¶</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torchjd.aggregation.MGDA">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torchjd.aggregation.</span></span><span class="sig-name descname"><span class="pre">MGDA</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epsilon</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_iters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/TorchJD/torchjd/blob/main/src/torchjd/aggregation/_mgda.py#L8-L42"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchjd.aggregation.MGDA" 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.</span></span><span class="sig-name descname"><span class="pre">MGDA</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epsilon</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_iters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/TorchJD/torchjd/blob/main/src/torchjd/aggregation/_mgda.py#L8-L40"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchjd.aggregation.MGDA" title="Link to this definition">¶</a></dt>
 <dd><p><a class="reference internal" href="../bases/#torchjd.aggregation.Aggregator" title="torchjd.aggregation._aggregator_bases.Aggregator"><code class="xref py py-class docutils literal notranslate"><span class="pre">Aggregator</span></code></a> performing the gradient aggregation
 step of <a class="reference external" href="https://www.sciencedirect.com/science/article/pii/S1631073X12000738">Multiple-gradient descent algorithm (MGDA) for multiobjective optimization</a>. The implementation is
 based on Algorithm 2 of <a class="reference external" href="https://proceedings.neurips.cc/paper_files/paper/2018/file/432aca3a1e345e339f35a30c8f65edce-Paper.pdf">Multi-Task Learning as Multi-Objective Optimization</a>.</p>

latest/docs/aggregation/nash_mtl/index.html

@@ -242,7 +242,7 @@
 <h1>Nash-MTL<a class="headerlink" href="#nash-mtl" title="Link to this heading">¶</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torchjd.aggregation.NashMTL">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torchjd.aggregation.</span></span><span class="sig-name descname"><span class="pre">NashMTL</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_tasks</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">update_weights_every</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_niter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">20</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/TorchJD/torchjd/blob/main/src/torchjd/aggregation/_nash_mtl.py#L41-L108"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchjd.aggregation.NashMTL" 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.</span></span><span class="sig-name descname"><span class="pre">NashMTL</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_tasks</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">update_weights_every</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_niter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">20</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/TorchJD/torchjd/blob/main/src/torchjd/aggregation/_nash_mtl.py#L41-L115"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchjd.aggregation.NashMTL" title="Link to this definition">¶</a></dt>
 <dd><p><a class="reference internal" href="../bases/#torchjd.aggregation.Aggregator" title="torchjd.aggregation._aggregator_bases.Aggregator"><code class="xref py py-class docutils literal notranslate"><span class="pre">Aggregator</span></code></a> as proposed in Algorithm 1 of
 <a class="reference external" href="https://arxiv.org/pdf/2202.01017.pdf">Multi-Task Learning as a Bargaining Game</a>.</p>
 <dl class="field-list simple">
@@ -291,7 +291,7 @@ <h1>Nash-MTL<a class="headerlink" href="#nash-mtl" title="Link to this heading">
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torchjd.aggregation.NashMTL.reset">
-<span class="sig-name descname"><span class="pre">reset</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/TorchJD/torchjd/blob/main/src/torchjd/aggregation/_nash_mtl.py#L103-L105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchjd.aggregation.NashMTL.reset" title="Link to this definition">¶</a></dt>
+<span class="sig-name descname"><span class="pre">reset</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/TorchJD/torchjd/blob/main/src/torchjd/aggregation/_nash_mtl.py#L107-L109"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torchjd.aggregation.NashMTL.reset" title="Link to this definition">¶</a></dt>
 <dd><p>Resets the internal state of the algorithm.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type<span class="colon">:</span></dt>