Deployed 52425f6 to 0.12.1 with MkDocs 1.6.0 and mike 2.1.2

0.12.1/index.html

@@ -4410,34 +4410,22 @@ <h1 id="neural-pipeline-search-neps">Neural Pipeline Search (NePS)<a class="head
 <h2 id="key-features">Key Features<a class="headerlink" href="#key-features" title="Permanent link">#</a></h2>
 <p>In addition to the features offered by traditional HPO and NAS libraries, NePS, e.g., stands out with:</p>
 <ol>
-<li>
-<p><a href="./examples/template/priorband_template.py"><strong>Hyperparameter Optimization (HPO) with Prior Knowledge and Cheap Proxies:</strong></a></p>
-</li>
-<li>
-<p>NePS excels in efficiently tuning hyperparameters using algorithms that enable users to make use of their prior knowledge within the search space. This is leveraged by the insights presented in:</p>
-<ul>
-<li><a href="https://arxiv.org/abs/2306.12370">PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning</a></li>
-<li><a href="https://arxiv.org/abs/2204.11051">πBO: Augmenting Acquisition Functions with User Beliefs for Bayesian Optimization</a></li>
-</ul>
-</li>
-<li>
-<p><a href="./examples/basic_usage/architecture.py"><strong>Neural Architecture Search (NAS) with General Search Spaces:</strong></a></p>
-</li>
-<li>
-<p>NePS is equipped to handle context-free grammar search spaces, providing advanced capabilities for designing and optimizing architectures. this is leveraged by the insights presented in:</p>
-<ul>
-<li><a href="https://arxiv.org/abs/2211.01842">Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars</a></li>
-</ul>
-</li>
-<li>
-<p><a href="https://automl.github.io/neps/latest/examples/efficiency/"><strong>Easy Parallelization and Tailored to DL:</strong></a></p>
-</li>
-<li>
-<p>NePS simplifies the process of parallelizing optimization tasks both on individual computers and in distributed
-     computing environments. As NePS is made for deep learners, all technical choices are made with DL in mind and common
-     DL tools such as Tensorboard are <a href="https://automl.github.io/neps/latest/reference/analyse/#visualizing-results">embraced</a>.</p>
-</li>
+<li><a href="./examples/template/priorband_template.py"><strong>Hyperparameter Optimization (HPO) with Prior Knowledge and Cheap Proxies:</strong></a></li>
 </ol>
+<p>NePS excels in efficiently tuning hyperparameters using algorithms that enable users to make use of their prior knowledge within the search space. This is leveraged by the insights presented in:
+    - <a href="https://arxiv.org/abs/2306.12370">PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning</a>
+    - <a href="https://arxiv.org/abs/2204.11051">πBO: Augmenting Acquisition Functions with User Beliefs for Bayesian Optimization</a></p>
+<ol>
+<li><a href="./examples/basic_usage/architecture.py"><strong>Neural Architecture Search (NAS) with General Search Spaces:</strong></a></li>
+</ol>
+<p>NePS is equipped to handle context-free grammar search spaces, providing advanced capabilities for designing and optimizing architectures. this is leveraged by the insights presented in:
+    - <a href="https://arxiv.org/abs/2211.01842">Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars</a></p>
+<ol>
+<li><a href="https://automl.github.io/neps/latest/examples/efficiency/"><strong>Easy Parallelization and Tailored to DL:</strong></a></li>
+</ol>
+<p>NePS simplifies the process of parallelizing optimization tasks both on individual computers and in distributed
+computing environments. As NePS is made for deep learners, all technical choices are made with DL in mind and common
+DL tools such as Tensorboard are <a href="https://automl.github.io/neps/latest/reference/analyse/#visualizing-results">embraced</a>.</p>
 <div class="admonition tip">
 <p class="admonition-title">Tip</p>
 <p>Check out:</p>