:orphan:

|rss_image|  **papers - 1/1** :ref:`Blog <ap-main-0>` :ref:`article (8) <ap-cat-article-0>` :ref:`articles (3) <ap-cat-articles-0>` :ref:`cours (6) <ap-cat-cours-0>` :ref:`module (7) <ap-cat-module-0>` :ref:`paper (3) <ap-cat-paper-0>`

.. |rss_image| image:: feed-icon-16x16.png
    :target: ../_downloads/rss.xml
    :alt: RSS

----


.. index:: papers


.. _ap-cat-papers-0:

papers - 1/1
++++++++++++

.. blogpostagg::
    :title: Articles, liens, code efficaces
    :date: 2022-06-28
    :keywords: implémentation
    :categories: papers
    :rawfile: 2022/2022-06-28_module.rst

    * `pyornear <https://pyronear.org/>`_ : détection de départs de feux
    * `Réseaux sociaux : la modélisation mathématique peut-elle contribuer à réduire la polarisation des opinions ?
      <https://www.inria.fr/fr/reseaux-sociaux-biais-cognitifs-modelisation-mathematique>`_
    * `dowhy <https://github.com/py-why/dowhy>`_ : An end-to-end library for causal inference
    * `merlion <https://github.com/salesforce/Merlion>`_ A Machine Learning Library for Time Series
    * `On the Convergence of Adam and Beyond <https://arxiv.org/abs/1904.09237>`_
    * `A Path Towards Autonomous Machine Intelligence
      <https://openreview.net/forum?id=BZ5a1r-kVsf>`_
    * `Gradient Descent Provably Optimizes Over-parameterized Neural Networks
      <https://arxiv.org/abs/1810.02054>`_
    * `jupyterlite <https://jupyterlite.readthedocs.io/en/latest/>`_




.. blogpostagg::
    :title: Articles, liens, code efficaces
    :date: 2021-03-24
    :keywords: implémentation
    :categories: papers
    :rawfile: 2021/2021-03-24_fast.rst

    * `How to optimize GEMM on CPU
      <https://tvm.apache.org/docs/tutorials/optimize/opt_gemm.html#sphx-glr-tutorials-optimize-opt-gemm-py>`_
    * `HIGH PERFORMANCE CODE GENERATION IN MLIR: AN EARLY CASE STUDY WITH GEMM
      <https://arxiv.org/pdf/2003.00532v1.pdf>`_
    * `Fireiron: A Data-Movement-Aware Scheduling Language for GPUs
      <https://dl.acm.org/doi/pdf/10.1145/3410463.3414632>`_
    * `Linalg Dialect Rationale: The Case For Compiler-Friendly Custom Operations
      <https://mlir.llvm.org/docs/Rationale/RationaleLinalgDialect/>`_
    * `Robocode
      <https://robocode.sourceforge.io/>`_
    * `Introducing PyTorch Profiler - the new and improved performance tool
      <https://pytorch.org/blog/introducing-pytorch-profiler-the-new-and-improved-performance-tool/>`_




.. blogpostagg::
    :title: Quelques vidéos de PyCon
    :date: 2020-05-01
    :keywords: pycon,conférences
    :categories: papers
    :rawfile: 2020/2020-05-01_pycon.rst

    Première vidéo à propos de "privacy" ou protection des données :
    `tensorflow_privacy <https://github.com/tensorflow/privacy>`_,
    `Practical privacy-preserving machine learning in Python
    <https://www.youtube.com/watch?v=NUk6QN02UxQ>`_.
    

    ...




.. blogpostagg::
    :title: Worst case scenarios
    :date: 2020-04-08
    :keywords: tree,branch bound
    :categories: papers
    :rawfile: 2020/2020-04-08_paper.rst

    J'ai découvert les publications de
    `Maria-Florina Balcan <https://www.csd.cs.cmu.edu/people/faculty/maria-balcan>`_
    aujourd'hui. Un de ses axes de recherches est - je cite -
    **Analysis of Algorithms beyond the Worst Case**.
    Celui-ci propose une amélioration de la construction d'arbres
    utilisés pour optimiser la recherche d'éléments dans
    un espace vectoriel : `Learning to Branch
    <http://www.cs.cmu.edu/~ninamf/papers/learn-branch.pdf>`_.
    Je recommande aussi les livres cités sur la page de son cours :
    `Advanced Introduction to Machine Learning <http://www.cs.cmu.edu/~10715-f18/>`_.
    Parmi ceux que j'ai envie de lire :
    `The Power of Localization
    for Efficiently Learning Linear Separators with Noise
    <http://www.cs.cmu.edu/~ninamf/papers/ABL16_malicious_jacm.pdf>`_,
    `Data Driven Resource Allocation for Distributed Learning
    <http://www.cs.cmu.edu/~ninamf/papers/data-driven-resource-allocation.pdf>`_,
    `Learning Valuation Functions
    <http://www.cs.cmu.edu/~ninamf/papers/learn-vals.pdf>`_,
    `Dispersion for Data-Driven Algorithm Design, Online Learning, and Private Optimization
    <https://arxiv.org/pdf/1711.03091.pdf>`_.
    

    ...




.. blogpostagg::
    :title: Articles
    :date: 2020-02-20
    :keywords: articles
    :categories: papers
    :rawfile: 2020/2020-02-24_review.rst

    La librairie `deslib
    <https://deslib.readthedocs.io/en/latest/index.html>`_
    implémente plusieurs algorithme de sélection de modèles
    sur des problèmes de classifications. Mais plutôt que
    de sélectionner un modèle ou un ensemble de modèle
    sur toutes la base, elle sélectionne les meilleurs
    modèles localement. On appelle cela la
    `sélection dynamique de classifieurs
    <https://www.sciencedirect.com/science/article/pii/S1566253517304074>`_
    (voir :ref:`l-dynamic-selection-ml`).
    

    ...





----

|rss_image|  **papers - 1/1** :ref:`2022-10 (1) <ap-month-2022-10-0>` :ref:`2022-12 (2) <ap-month-2022-12-0>` :ref:`2023-01 (1) <ap-month-2023-01-0>` :ref:`2023-02 (1) <ap-month-2023-02-0>` :ref:`2023-04 (1) <ap-month-2023-04-0>`