:orphan:

=============================
tlmnet Examples Gallery
=============================

This gallery provides practitioner-focused examples demonstrating how to leverage
``TlmMilpClassifier`` for exact ternary linear modeling, strict :math:`L_0` feature
cardinality budgeting, and sparse text classification.

Together, these scripts illustrate how exact Mixed-Integer Linear Programming (MILP)
replaces greedy heuristic approximations, yielding globally optimal integer-weighted
models compliant with Scikit-Learn 1.6+ workflows.

Gallery Highlights
------------------

* **Exact L0 Feature Selection Budgeting:**
  Demonstrates how to enforce hard integer cardinality constraints using the ``max_features`` parameter on the Breast Cancer dataset to build ultra-sparse, highly interpretable scorecards.
  *(See: Exact L0 Sparsity Budgeting on Breast Cancer Dataset)*

* **Multiclass One-vs-Rest Text Classification:**
  Demonstrates how ``TlmMilpClassifier`` integrates seamlessly with Scikit-Learn's ``OneVsRestClassifier`` to perform exact multi-class document classification.
  *(See: Multilabel Text Document Classification with Exact MILP One-vs-Rest)*

* **Runtime Scaling & Solver Performance:**
  Quantifies branch-and-bound solve times across varying feature dimensions (:math:`p`) and sample sizes (:math:`n`).
  *(See: MILP Solve Time vs. Feature & Sample Dimensions)*

* **Decision Boundaries & Surface Visualization:**
  Visualizes the discrete, quantized decision surfaces created by ternary weight vectors :math:`w_j \in \{-1, 0, 1\}` on 2D feature spaces.
  *(See: Decision Boundaries & Margin Scores)*

* **Sparse Text Matrix Classification:**
  Shows how to pair ``TfidfVectorizer`` natively with ``TlmMilpClassifier`` using sparse SciPy block matrices.
  *(See: Sparse Text Classification with Vocabulary Limits)*


.. raw:: html

  <div id='sg-tag-list' class='sphx-glr-tag-list'></div>


.. raw:: html

    <div class="sphx-glr-thumbnails">

.. thumbnail-parent-div-open

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example evaluates how execution time scales with feature count p and sample size n when optimizing exact ternary weights via MILP.">

.. only:: html

  .. image:: /auto_examples/images/thumb/sphx_glr_plot_runtime_vs_performance_thumb.png
    :alt:

  :doc:`/auto_examples/plot_runtime_vs_performance`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">MILP Solve Time vs. Feature & Sample Dimensions</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Visualizes the discrete decision boundaries generated by ternary weights w_j \in \{-1, 0, 1\} on a 2D synthetic dataset.">

.. only:: html

  .. image:: /auto_examples/images/thumb/sphx_glr_plot_decision_thresholds_thumb.png
    :alt:

  :doc:`/auto_examples/plot_decision_thresholds`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Decision Boundaries & Margin Scores</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Shows how to pair TfidfVectorizer with TlmMilpClassifier by constraining vocabulary dimension to prevent exponential MILP solver time, visualizing the resulting ternary text weights.">

.. only:: html

  .. image:: /auto_examples/images/thumb/sphx_glr_plot_classify_newsgroups_thumb.png
    :alt:

  :doc:`/auto_examples/plot_classify_newsgroups`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Sparse Text Classification with Vocabulary Limits</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Demonstrates exact cardinality constraints via max_features against an L1 Logistic Regression baseline on the Breast Cancer dataset.">

.. only:: html

  .. image:: /auto_examples/images/thumb/sphx_glr_plot_feature_selection_breast_cancer_thumb.png
    :alt:

  :doc:`/auto_examples/plot_feature_selection_breast_cancer`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Exact L0 Sparsity Budgeting on Breast Cancer Dataset</div>
    </div>


.. thumbnail-parent-div-close

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_runtime_vs_performance
   /auto_examples/plot_decision_thresholds
   /auto_examples/plot_classify_newsgroups
   /auto_examples/plot_feature_selection_breast_cancer



.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_