regularization.html



<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
  <meta charset="utf-8">
  
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
  
  <title>Regularization in PaddlePaddle &mdash; PaddlePaddle  documentation</title>
  

    <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
  

        <link rel="index" title="Index"
              href="../genindex.html"/>
        <link rel="search" title="Search" href="../search.html"/>
    <link rel="top" title="PaddlePaddle  documentation" href="../index.html"/> 

  <link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
  <link rel="stylesheet" href="../_static/css/override.css" type="text/css" />
  <script>
  var _hmt = _hmt || [];
  (function() {
    var hm = document.createElement("script");
    hm.src = "//hm.baidu.com/hm.js?b9a314ab40d04d805655aab1deee08ba";
    var s = document.getElementsByTagName("script")[0]; 
    s.parentNode.insertBefore(hm, s);
  })();
  </script>

  
  <script src="../_static/js/modernizr.min.js"></script>

</head>

<body class="wy-body-for-nav" role="document">

  
  <header class="site-header">
    <div class="site-logo">
      <a href="/"><img src="../_static/images/PP_w.png"></a>
    </div>
    <div class="site-nav-links">
      <div class="site-menu">
        <a class="fork-on-github" href="https://github.com/PaddlePaddle/Paddle" target="_blank"><i class="fa fa-github"></i>Fork me on Github</a>
        <div class="language-switcher dropdown">
          <a type="button" data-toggle="dropdown">
            <span>English</span>
            <i class="fa fa-angle-up"></i>
            <i class="fa fa-angle-down"></i>
          </a>
          <ul class="dropdown-menu">
            <li><a href="/doc_cn">中文</a></li>
            <li><a href="/doc">English</a></li>
          </ul>
        </div>
        <ul class="site-page-links">
          <li><a href="/">Home</a></li>
        </ul>
      </div>
      <div class="doc-module">
        
        <ul>
<li class="toctree-l1"><a class="reference internal" href="../getstarted/index_en.html">GET STARTED</a></li>
<li class="toctree-l1"><a class="reference internal" href="../howto/index_en.html">HOW TO</a></li>
<li class="toctree-l1"><a class="reference internal" href="../api/index_en.html">API</a></li>
</ul>

        
<div role="search">
  <form id="rtd-search-form" class="wy-form" action="../search.html" method="get">
    <input type="text" name="q" placeholder="Search docs" />
    <input type="hidden" name="check_keywords" value="yes" />
    <input type="hidden" name="area" value="default" />
  </form>
</div>        
      </div>
    </div>
  </header>
  
  <div class="main-content-wrap">

    
    <nav class="doc-menu-vertical" role="navigation">
        
          
          <ul>
<li class="toctree-l1"><a class="reference internal" href="../getstarted/index_en.html">GET STARTED</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../getstarted/build_and_install/index_en.html">Install and Build</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../getstarted/build_and_install/docker_install_en.html">PaddlePaddle in Docker Containers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../getstarted/build_and_install/build_from_source_en.html">Installing from Sources</a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../howto/index_en.html">HOW TO</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../howto/usage/cmd_parameter/index_en.html">Set Command-line Parameters</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../howto/usage/cmd_parameter/use_case_en.html">Use Case</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/usage/cmd_parameter/arguments_en.html">Argument Outline</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/usage/cmd_parameter/detail_introduction_en.html">Detail Description</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../howto/usage/cluster/cluster_train_en.html">PaddlePaddle Distributed Training</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/usage/cluster/cluster_train_en.html#introduction">Introduction</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/usage/cluster/cluster_train_en.html#preparations">Preparations</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/usage/cluster/cluster_train_en.html#command-line-arguments">Command-line arguments</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/usage/cluster/cluster_train_en.html#use-cluster-platforms-or-cluster-management-tools">Use cluster platforms or cluster management tools</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/usage/k8s/k8s_en.html">Paddle On Kubernetes</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/dev/build_en.html">Build PaddlePaddle from Source Code and Run Unit Test</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/dev/new_layer_en.html">Write New Layers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../api/index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/evaluators.html">Evaluators</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/data.html">Data Reader Interface and DataSets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
</ul>

        
    </nav>
    
    <section class="doc-content-wrap">

      
<div role="navigation" aria-label="breadcrumbs navigation">
  <ul class="wy-breadcrumbs">
      
    <li>Regularization in PaddlePaddle</li>
  </ul>
</div>
      
      <div class="wy-nav-content" id="doc-content">
        <div class="rst-content">
          <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
           <div itemprop="articleBody">
            
  <div class="section" id="regularization-in-paddlepaddle">
<span id="regularization-in-paddlepaddle"></span><h1>Regularization in PaddlePaddle<a class="headerlink" href="#regularization-in-paddlepaddle" title="Permalink to this headline">¶</a></h1>
<div class="section" id="introduction-to-regularization">
<span id="introduction-to-regularization"></span><h2>Introduction to Regularization<a class="headerlink" href="#introduction-to-regularization" title="Permalink to this headline">¶</a></h2>
<p>A central problem in machine learning is how to design an algorithm that will perform well not just on the training data, but also on new data. Many strategies are used by machine learning practitioners to reduce the test error, possibly at the expense of increased training error. These strategies are collectively known as <strong>regularization</strong>.</p>
<div class="section" id="parameter-norm-penalties">
<span id="parameter-norm-penalties"></span><h3>Parameter Norm Penalties<a class="headerlink" href="#parameter-norm-penalties" title="Permalink to this headline">¶</a></h3>
<p>Most common regularization approaches in deep learning are based on limiting the capacity of the models by adding a parameter norm penalty to the objective function <code class="docutils literal"><span class="pre">J</span></code>. This is given as follows:</p>
<p><img src="./images/loss_equation.png" align="center"/><br/></p>
<p>The parameter <code class="docutils literal"><span class="pre">alpha</span></code> is a hyperparameter that weights the relative contribution of the norm penalty term, <code class="docutils literal"><span class="pre">omega</span></code>, relative to the standard objective function <code class="docutils literal"><span class="pre">J</span></code>.</p>
<p>The most commonly used norm penalties are the L2 norm penalty and the L1 norm penalty. These are given as follows:</p>
<div class="section" id="l2-regularization">
<span id="l2-regularization"></span><h4>L2 Regularization:<a class="headerlink" href="#l2-regularization" title="Permalink to this headline">¶</a></h4>
<p><img src="./images/l2_regularization.png" align="center"/><br/></p>
</div>
<div class="section" id="l1-regularization">
<span id="l1-regularization"></span><h4>L1 Regularization<a class="headerlink" href="#l1-regularization" title="Permalink to this headline">¶</a></h4>
<p><img src="./images/l1_regularization.png" align="center"/><br/></p>
<p>A much more detailed mathematical background of reguilarization can be found <a class="reference external" href="http://www.deeplearningbook.org/contents/regularization.html">here</a>.</p>
</div>
</div>
</div>
<div class="section" id="how-to-do-regularization-in-paddlepaddle">
<span id="how-to-do-regularization-in-paddlepaddle"></span><h2>How to do Regularization in PaddlePaddle<a class="headerlink" href="#how-to-do-regularization-in-paddlepaddle" title="Permalink to this headline">¶</a></h2>
<p>On surveying existing frameworks like Tensorflow, PyTorch, Caffe, etc, it can be seen that there are 2 common approaches of doing regularization:</p>
<ol>
<li><p class="first">Making regularization a part of the optimizer using an attribute like <code class="docutils literal"><span class="pre">weight_decay</span></code> that is used to control the scale of the L2 Penalty. This approach is used in PyTorch as follows:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">opt</span> <span class="o">=</span>  <span class="n">torch</span><span class="o">.</span><span class="n">optim</span><span class="o">.</span><span class="n">SGD</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="n">lr</span><span class="o">=</span><span class="mf">0.2</span><span class="p">,</span> <span class="n">weight_decay</span><span class="o">=</span><span class="mf">0.2</span><span class="p">)</span>
</pre></div>
</div>
<p>At every optimization step, this code will add the gradient of the L2 Norm of the params to the gradient of the params with respect to the loss function. This can seen in the following code snippet:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="k">if</span> <span class="n">weight_decay</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span>
    <span class="n">d_p</span><span class="o">.</span><span class="n">add_</span><span class="p">(</span><span class="n">weight_decay</span><span class="p">,</span> <span class="n">p</span><span class="o">.</span><span class="n">data</span><span class="p">)</span>
</pre></div>
</div>
<p>This is a very restyrictive way of doing regularization and does not give the users enough flexibility.</p>
<p><strong>Advantages</strong>:</p>
<ul class="simple">
<li>It is easy to implement for us.</li>
<li>Faster execution of backward. However, it can be done manually by advanced users too.</li>
</ul>
<p><strong>Disadvantages</strong>:</p>
<ul class="simple">
<li>Not flexible for other regularizations such as L1/L0 regularization.</li>
<li>Does not allow for different regularization coefficient for different parameters. For example, in most models, ony the weight matrices are regularized and the bias vectors are unregularized.</li>
<li>Tightly coupled optimizer and regularization implementation.</li>
</ul>
</li>
</ol>
<ol>
<li><p class="first">Adding regularization ops to the graph through Python API. This approach is used by Tensorflow and Caffe. Using this approach, we manually add regularization ops to the graph and then add the regularization loss to the final loss function before sending them to the optimizer.</p>
<p><strong>Advantages</strong>:</p>
<ul class="simple">
<li>Allows for greater flexibility to the users of Paddle. Using this approach, the users can put different regularization to different parameters and also choose parameters that are not a part of regularization.</li>
<li>Makes it easy for the users to customize and extend the framework.</li>
</ul>
<p><strong>Disadvantages</strong>:</p>
<ul class="simple">
<li>Implementation requires comprehensive design and time.</li>
</ul>
</li>
</ol>
</div>
<div class="section" id="proposal-for-regularization-in-paddlepaddle">
<span id="proposal-for-regularization-in-paddlepaddle"></span><h2>Proposal for Regularization in PaddlePaddle<a class="headerlink" href="#proposal-for-regularization-in-paddlepaddle" title="Permalink to this headline">¶</a></h2>
<div class="section" id="low-level-implementation">
<span id="low-level-implementation"></span><h3>Low-Level implementation<a class="headerlink" href="#low-level-implementation" title="Permalink to this headline">¶</a></h3>
<p>In the new design, we propose to create new operations for regularization. For now, we can add 2 ops thgat correspond to the most frequently used regularizations:</p>
<ul class="simple">
<li>L2_regularization_op</li>
<li>L1_regularization_op</li>
</ul>
<p>These ops can be like any other ops with their own CPU/GPU implementations either using Eigen or separate Cpu and GPU kernels. As the initial implementation, we can implement their kernels using Eigen following the abstraction pattern implemented for <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/operators/accuracy_op.h">Activation Ops</a>. This abstraction pattern can make it very easy to implement new regularization schemes. other than L1 and L2 norm penalties.</p>
<p>The idea of building ops for regularization is in sync with the refactored Paddle philosophy of using operators to represent any computation unit. The way these ops will be added to the computation graph, will be decided by the <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/doc/design/python_api.md#layer-function">layer functions</a> in Python API.</p>
</div>
<div class="section" id="computation-graph">
<span id="computation-graph"></span><h3>Computation Graph<a class="headerlink" href="#computation-graph" title="Permalink to this headline">¶</a></h3>
<p>Below is an example of a really simple feed forward neural network.</p>
<p><img src="./images/feed_forward.png" align="center"/><br/></p>
<p>The Python API will modify this computation graph to add regularization operators. The modified computation graph will look as follows:</p>
<p><img src="./images/feed_forward_regularized.png" align="center"/><br/></p>
</div>
<div class="section" id="python-api-implementation-for-regularization">
<span id="python-api-implementation-for-regularization"></span><h3>Python API implementation for Regularization<a class="headerlink" href="#python-api-implementation-for-regularization" title="Permalink to this headline">¶</a></h3>
<p>Using the low level ops, <code class="docutils literal"><span class="pre">L2_regularization_op</span></code> and <code class="docutils literal"><span class="pre">L1_regularization_op</span></code>, any user can add regularization to their computation graphs. However, this will require a lot of lines of code and we should design Python APIs that support regularization. An example of such an API can be seen in <a class="reference external" href="https://keras.io/regularizers/">Keras</a>. As per the PaddlePaddle <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/doc/design/python_api.md">Python API design</a>, the layer functions are responsible for creating operators, operator parameters and variables. Since regularization is a property of parameters, it makes sense to create these in the layer functions.</p>
<div class="section" id="creation-of-regularization-ops">
<span id="creation-of-regularization-ops"></span><h4>Creation of Regularization ops<a class="headerlink" href="#creation-of-regularization-ops" title="Permalink to this headline">¶</a></h4>
<p>There are two possibilities for creating the regularization ops:</p>
<ol class="simple">
<li>We create these ops immediately while building the computation graph.</li>
<li>We add these ops in a lazy manner, just before the backward, similar to the way the optimization ops are added.</li>
</ol>
<p>The proposal is to add these ops in a lazy manner just before the backward pass.</p>
</div>
<div class="section" id="storage-of-regularization-attributes">
<span id="storage-of-regularization-attributes"></span><h4>Storage of Regularization attributes<a class="headerlink" href="#storage-of-regularization-attributes" title="Permalink to this headline">¶</a></h4>
<p>Since we want to create the regularization ops in a lazy manner, the regularization attributes (type of regularization and weight of regularization penalty) can be stored as attributes of the <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/v2/framework/framework.py#L421"><code class="docutils literal"><span class="pre">Parameter</span></code></a> class. This is because regularization is a property of the parameters and storing regularization properties with Parameters also allows for shared parameters.</p>
</div>
<div class="section" id="high-level-api">
<span id="high-level-api"></span><h4>High-level API<a class="headerlink" href="#high-level-api" title="Permalink to this headline">¶</a></h4>
<p>In PaddlePaddle Python API, users will primarily rely on <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/doc/design/python_api.md#layer-function">layer functions</a> to create neural network layers. Hence, we lso need to provide regularization functionality in layer functions. The design of these APIs can be postponed for later right now. A good reference for these APIs can be found in <a class="reference external" href="https://keras.io/regularizers/">Keras</a> and also by looking at Tensorflow in <a class="reference external" href="https://www.tensorflow.org/api_guides/python/contrib.layers"><code class="docutils literal"><span class="pre">tf.contrib.layers</span></code></a>.</p>
</div>
</div>
</div>
</div>


           </div>
          </div>
          <footer>
  

  <hr/>

  <div role="contentinfo">
    <p>
        &copy; Copyright 2016, PaddlePaddle developers.

    </p>
  </div>
  Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. 

</footer>

        </div>
      </div>

    </section>

  </div>
  

    <script type="text/javascript">
        var DOCUMENTATION_OPTIONS = {
            URL_ROOT:'../',
            VERSION:'',
            COLLAPSE_INDEX:false,
            FILE_SUFFIX:'.html',
            HAS_SOURCE:  true,
            SOURCELINK_SUFFIX: ".txt",
        };
    </script>
      <script type="text/javascript" src="../_static/jquery.js"></script>
      <script type="text/javascript" src="../_static/underscore.js"></script>
      <script type="text/javascript" src="../_static/doctools.js"></script>
      <script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>
       
  
    <script type="text/javascript" src="../_static/js/theme.js"></script>
  
  
  <script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/js/bootstrap.min.js" integrity="sha384-Tc5IQib027qvyjSMfHjOMaLkfuWVxZxUPnCJA7l2mCWNIpG9mGCD8wGNIcPD7Txa" crossorigin="anonymous"></script>
  <script src="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/js/perfect-scrollbar.jquery.min.js"></script>
  <script src="../_static/js/paddle_doc_init.js"></script> 

</body>
</html>