diff --git a/src/mlpack/core/optimizers/ada_delta/ada_delta.hpp b/src/mlpack/core/optimizers/ada_delta/ada_delta.hpp
index 8589374460..9a209c63e7 100644
--- a/src/mlpack/core/optimizers/ada_delta/ada_delta.hpp
+++ b/src/mlpack/core/optimizers/ada_delta/ada_delta.hpp
@@ -34,10 +34,10 @@ namespace optimization {
  *
  * @code
  * @article{Zeiler2012,
- *   author    = {Matthew D. Zeiler},
- *   title     = {{ADADELTA:} An Adaptive Learning Rate Method},
- *   journal   = {CoRR},
- *   year      = {2012}
+ *   author  = {Matthew D. Zeiler},
+ *   title   = {{ADADELTA:} An Adaptive Learning Rate Method},
+ *   journal = {CoRR},
+ *   year    = {2012}
  * }
  * @endcode
  *
diff --git a/src/mlpack/core/optimizers/ada_delta/ada_delta_update.hpp b/src/mlpack/core/optimizers/ada_delta/ada_delta_update.hpp
index 391e2a88bd..fc3d0bcde0 100644
--- a/src/mlpack/core/optimizers/ada_delta/ada_delta_update.hpp
+++ b/src/mlpack/core/optimizers/ada_delta/ada_delta_update.hpp
@@ -29,10 +29,10 @@ namespace optimization {
  *
  * @code
  * @article{Zeiler2012,
- *   author    = {Matthew D. Zeiler},
- *   title     = {{ADADELTA:} An Adaptive Learning Rate Method},
- *   journal   = {CoRR},
- *   year      = {2012}
+ *   author  = {Matthew D. Zeiler},
+ *   title   = {{ADADELTA:} An Adaptive Learning Rate Method},
+ *   journal = {CoRR},
+ *   year    = {2012}
  * }
  * @endcode
  *
diff --git a/src/mlpack/core/optimizers/ada_grad/ada_grad.hpp b/src/mlpack/core/optimizers/ada_grad/ada_grad.hpp
index e96b619e85..6c622c8e3e 100644
--- a/src/mlpack/core/optimizers/ada_grad/ada_grad.hpp
+++ b/src/mlpack/core/optimizers/ada_grad/ada_grad.hpp
@@ -30,13 +30,13 @@ namespace optimization {
  *
  * @code
  * @article{duchi2011adaptive,
- *   author    = {Duchi, John and Hazan, Elad and Singer, Yoram},
- *   title     = {Adaptive subgradient methods for online learning and stochastic optimization},
- *   journal   = {Journal of Machine Learning Research},
- *   volume    = {12},
- *   number    = {Jul},
- *   pages     = {2121--2159},
- *   year      = {2011}
+ *   author  = {Duchi, John and Hazan, Elad and Singer, Yoram},
+ *   title   = {Adaptive subgradient methods for online learning and stochastic optimization},
+ *   journal = {Journal of Machine Learning Research},
+ *   volume  = {12},
+ *   number  = {Jul},
+ *   pages   = {2121--2159},
+ *   year    = {2011}
  * }
  * @endcode
  *
diff --git a/src/mlpack/core/optimizers/ada_grad/ada_grad_update.hpp b/src/mlpack/core/optimizers/ada_grad/ada_grad_update.hpp
index 2fb52573b1..b086926388 100644
--- a/src/mlpack/core/optimizers/ada_grad/ada_grad_update.hpp
+++ b/src/mlpack/core/optimizers/ada_grad/ada_grad_update.hpp
@@ -58,8 +58,8 @@ class AdaGradUpdate
    * gradient matrix is initialized to the zeros matrix with the same size as
    * gradient matrix (see mlpack::optimization::SGD::Optimizer).
    *
-   * @param rows number of rows in the gradient matrix.
-   * @param cols number of columns in the gradient matrix.
+   * @param rows Number of rows in the gradient matrix.
+   * @param cols Number of columns in the gradient matrix.
    */
   void Initialize(const size_t rows,
                   const size_t cols)
diff --git a/src/mlpack/core/optimizers/adam/adam.hpp b/src/mlpack/core/optimizers/adam/adam.hpp
index d4808c6cd9..23615fdd9e 100644
--- a/src/mlpack/core/optimizers/adam/adam.hpp
+++ b/src/mlpack/core/optimizers/adam/adam.hpp
@@ -37,11 +37,11 @@ namespace optimization {
  *
  * @code
  * @article{Kingma2014,
- *   author    = {Diederik P. Kingma and Jimmy Ba},
- *   title     = {Adam: {A} Method for Stochastic Optimization},
- *   journal   = {CoRR},
- *   year      = {2014},
- *   url       = {http://arxiv.org/abs/1412.6980}
+ *   author  = {Diederik P. Kingma and Jimmy Ba},
+ *   title   = {Adam: {A} Method for Stochastic Optimization},
+ *   journal = {CoRR},
+ *   year    = {2014},
+ *   url     = {http://arxiv.org/abs/1412.6980}
  * }
  * @endcode
  *
@@ -95,13 +95,13 @@ class AdamType
    *        function is visited in linear order.
    */
   AdamType(DecomposableFunctionType& function,
-          const double stepSize = 0.001,
-          const double beta1 = 0.9,
-          const double beta2 = 0.999,
-          const double eps = 1e-8,
-          const size_t maxIterations = 100000,
-          const double tolerance = 1e-5,
-          const bool shuffle = true);
+           const double stepSize = 0.001,
+           const double beta1 = 0.9,
+           const double beta2 = 0.999,
+           const double eps = 1e-8,
+           const size_t maxIterations = 100000,
+           const double tolerance = 1e-5,
+           const bool shuffle = true);
 
   /**
    * Optimize the given function using Adam. The given starting point will be
diff --git a/src/mlpack/core/optimizers/adam/adam_update.hpp b/src/mlpack/core/optimizers/adam/adam_update.hpp
index b420b57311..0f64c82327 100644
--- a/src/mlpack/core/optimizers/adam/adam_update.hpp
+++ b/src/mlpack/core/optimizers/adam/adam_update.hpp
@@ -31,11 +31,11 @@ namespace optimization {
  *
  * @code
  * @article{Kingma2014,
- *   author    = {Diederik P. Kingma and Jimmy Ba},
- *   title     = {Adam: {A} Method for Stochastic Optimization},
- *   journal   = {CoRR},
- *   year      = {2014},
- *   url       = {http://arxiv.org/abs/1412.6980}
+ *   author  = {Diederik P. Kingma and Jimmy Ba},
+ *   title   = {Adam: {A} Method for Stochastic Optimization},
+ *   journal = {CoRR},
+ *   year    = {2014},
+ *   url     = {http://arxiv.org/abs/1412.6980}
  * }
  * @endcode
  */
@@ -65,8 +65,8 @@ class AdamUpdate
    * The Initialize method is called by SGD Optimizer method before the start of
    * the iteration update process.
    *
-   * @param rows number of rows in the gradient matrix.
-   * @param cols number of columns in the gradient matrix.
+   * @param rows Number of rows in the gradient matrix.
+   * @param cols Number of columns in the gradient matrix.
    */
   void Initialize(const size_t rows,
                   const size_t cols)
@@ -105,7 +105,7 @@ class AdamUpdate
      * m / (arma::sqrt(v) + (arma::sqrt(biasCorrection2) * eps).
      */
     iterate -= (stepSize * std::sqrt(biasCorrection2) / biasCorrection1) *
-                m / (arma::sqrt(v) + epsilon);
+        m / (arma::sqrt(v) + epsilon);
   }
 
   //! Get the value used to initialise the squared gradient parameter.
diff --git a/src/mlpack/core/optimizers/adam/adamax_update.hpp b/src/mlpack/core/optimizers/adam/adamax_update.hpp
index 6337efaae3..9ac281cca8 100644
--- a/src/mlpack/core/optimizers/adam/adamax_update.hpp
+++ b/src/mlpack/core/optimizers/adam/adamax_update.hpp
@@ -67,8 +67,8 @@ class AdaMaxUpdate
    * The Initialize method is called by SGD Optimizer method before the start of
    * the iteration update process.
    *
-   * @param rows number of rows in the gradient matrix.
-   * @param cols number of columns in the gradient matrix.
+   * @param rows Number of rows in the gradient matrix.
+   * @param cols Number of columns in the gradient matrix.
    */
   void Initialize(const size_t rows,
                   const size_t cols)
diff --git a/src/mlpack/core/optimizers/gradient_descent/gradient_descent.hpp b/src/mlpack/core/optimizers/gradient_descent/gradient_descent.hpp
index 78ee103813..79fb8dded7 100644
--- a/src/mlpack/core/optimizers/gradient_descent/gradient_descent.hpp
+++ b/src/mlpack/core/optimizers/gradient_descent/gradient_descent.hpp
@@ -66,9 +66,9 @@ class GradientDescent
    * @param tolerance Maximum absolute tolerance to terminate algorithm.
    */
   GradientDescent(FunctionType& function,
-      const double stepSize = 0.01,
-      const size_t maxIterations = 100000,
-      const double tolerance = 1e-5);
+                  const double stepSize = 0.01,
+                  const size_t maxIterations = 100000,
+                  const double tolerance = 1e-5);
 
   /**
    * Optimize the given function using gradient descent.  The given starting
diff --git a/src/mlpack/core/optimizers/rmsprop/rmsprop.hpp b/src/mlpack/core/optimizers/rmsprop/rmsprop.hpp
index 4d67dd906b..c3da802d70 100644
--- a/src/mlpack/core/optimizers/rmsprop/rmsprop.hpp
+++ b/src/mlpack/core/optimizers/rmsprop/rmsprop.hpp
@@ -38,9 +38,9 @@ namespace optimization {
  *
  * @code
  * @misc{tieleman2012,
- *   title={Lecture 6.5 - rmsprop, COURSERA: Neural Networks for Machine
- *   Learning},
- *   year={2012}
+ *   title = {Lecture 6.5 - rmsprop, COURSERA: Neural Networks for Machine
+ *            Learning},
+ *   year  = {2012}
  * }
  * @endcode
  *
diff --git a/src/mlpack/core/optimizers/rmsprop/rmsprop_update.hpp b/src/mlpack/core/optimizers/rmsprop/rmsprop_update.hpp
index b9a821a8c4..c86f09f0c3 100644
--- a/src/mlpack/core/optimizers/rmsprop/rmsprop_update.hpp
+++ b/src/mlpack/core/optimizers/rmsprop/rmsprop_update.hpp
@@ -35,9 +35,9 @@ namespace optimization {
  *
  * @code
  * @misc{tieleman2012,
- *   title={Lecture 6.5 - rmsprop, COURSERA: Neural Networks for Machine
- *   Learning},
- *   year={2012}
+ *   title = {Lecture 6.5 - rmsprop, COURSERA: Neural Networks for Machine
+ *            Learning},
+ *   year  = {2012}
  * }
  * @endcode
  */
@@ -63,8 +63,8 @@ class RMSPropUpdate
    * The Initialize method is called by SGD Optimizer method before the start of
    * the iteration update process.
    *
-   * @param rows number of rows in the gradient matrix.
-   * @param cols number of columns in the gradient matrix.
+   * @param rows Number of rows in the gradient matrix.
+   * @param cols Number of columns in the gradient matrix.
    */
   void Initialize(const size_t rows,
                   const size_t cols)
@@ -86,7 +86,8 @@ class RMSPropUpdate
   {
     meanSquaredGradient *= alpha;
     meanSquaredGradient += (1 - alpha) * (gradient % gradient);
-    iterate -= stepSize * gradient / (arma::sqrt(meanSquaredGradient) + epsilon);
+    iterate -= stepSize * gradient / (arma::sqrt(meanSquaredGradient) +
+        epsilon);
   }
 
   //! Get the value used to initialise the squared gradient parameter.
diff --git a/src/mlpack/core/optimizers/sgd/update_policies/momentum_update.hpp b/src/mlpack/core/optimizers/sgd/update_policies/momentum_update.hpp
index 2947c355f9..1ea0856034 100644
--- a/src/mlpack/core/optimizers/sgd/update_policies/momentum_update.hpp
+++ b/src/mlpack/core/optimizers/sgd/update_policies/momentum_update.hpp
@@ -42,23 +42,23 @@ namespace optimization {
  *
  * @code
  * @article{rumelhart1988learning,
- *   title={Learning representations by back-propagating errors},
- *   author={Rumelhart, David E. and Hinton, Geoffrey E. and
- *        Williams, Ronald J.},
- *   journal={Cognitive Modeling},
- *   volume={5},
- *   number={3},
- *   pages={1},
- *   year={1988}
+ *   title   = {Learning representations by back-propagating errors},
+ *   author  = {Rumelhart, David E. and Hinton, Geoffrey E. and
+ *              Williams, Ronald J.},
+ *   journal = {Cognitive Modeling},
+ *   volume  = {5},
+ *   number  = {3},
+ *   pages   = {1},
+ *   year    = {1988}
  * }
  *
  * @code
  * @book{Goodfellow-et-al-2016,
- *  title={Deep Learning},
- *  author={Ian Goodfellow and Yoshua Bengio and Aaron Courville},
- *  publisher={MIT Press},
- *  note={\url{http://www.deeplearningbook.org}},
- *  year={2016}
+ *  title     = {Deep Learning},
+ *  author    = {Ian Goodfellow and Yoshua Bengio and Aaron Courville},
+ *  publisher = {MIT Press},
+ *  note      = {\url{http://www.deeplearningbook.org}},
+ *  year      = {2016}
  * }
  */
 class MomentumUpdate
@@ -78,14 +78,14 @@ class MomentumUpdate
    * matrix is initialized to the zeros matrix with the same size as the
    * gradient matrix (see mlpack::optimization::SGD::Optimizer )
    *
-   * @param n_rows number of rows in the gradient matrix.
-   * @param n_cols number of columns in the gradient matrix.
+   * @param rows Number of rows in the gradient matrix.
+   * @param cols Number of columns in the gradient matrix.
    */
-  void Initialize(const size_t n_rows,
-                  const size_t n_cols)
+  void Initialize(const size_t rows,
+                  const size_t cols)
   {
     //Initialize am empty velocity matrix.
-    velocity = arma::zeros<arma::mat>(n_rows, n_cols);
+    velocity = arma::zeros<arma::mat>(rows, cols);
   }
 
   /**
diff --git a/src/mlpack/core/optimizers/sgd/update_policies/vanilla_update.hpp b/src/mlpack/core/optimizers/sgd/update_policies/vanilla_update.hpp
index 1bd85bf1c3..d76264864b 100644
--- a/src/mlpack/core/optimizers/sgd/update_policies/vanilla_update.hpp
+++ b/src/mlpack/core/optimizers/sgd/update_policies/vanilla_update.hpp
@@ -36,10 +36,10 @@ class VanillaUpdate
    * the iteration update process.  The vanilla update doesn't initialize
    * anything.
    *
-   * @param n_rows number of rows in the gradient matrix.
-   * @param n_cols number of columns in the gradient matrix.
+   * @param rows Number of rows in the gradient matrix.
+   * @param cols Number of columns in the gradient matrix.
    */
-  void Initialize(const size_t /* n_rows */, const size_t /* n_cols */)
+  void Initialize(const size_t /* rows */, const size_t /* cols */)
   { /* Do nothing. */ }
 
  /**
diff --git a/src/mlpack/core/optimizers/smorms3/smorms3.hpp b/src/mlpack/core/optimizers/smorms3/smorms3.hpp
index 41643c8023..d8b6749707 100644
--- a/src/mlpack/core/optimizers/smorms3/smorms3.hpp
+++ b/src/mlpack/core/optimizers/smorms3/smorms3.hpp
@@ -31,16 +31,16 @@ namespace optimization {
  *
  * @code
  * @misc{Funk2015,
- *   author    = {Simon Funk},
- *   title     = {RMSprop loses to SMORMS3 - Beware the Epsilon!},
- *   year      = {2015}
- *   url       = {http://sifter.org/~simon/journal/20150420.html}
+ *   author = {Simon Funk},
+ *   title  = {RMSprop loses to SMORMS3 - Beware the Epsilon!},
+ *   year   = {2015}
+ *   url    = {http://sifter.org/~simon/journal/20150420.html}
  * }
  * @endcode
  *
  *
- * For SMORMS3 to work, a DecomposableFunctionType template parameter is required.
- * This class must implement the following function:
+ * For SMORMS3 to work, a DecomposableFunctionType template parameter is
+ * required. This class must implement the following function:
  *
  *   size_t NumFunctions();
  *   double Evaluate(const arma::mat& coordinates, const size_t i);
@@ -57,7 +57,7 @@ namespace optimization {
  * is held internally in the DecomposableFunctionType).
  *
  * @tparam DecomposableFunctionType Decomposable objective function type to be
- *     minimized.
+ *         minimized.
  */
 template<typename DecomposableFunctionType>
 class SMORMS3
@@ -73,7 +73,8 @@ class SMORMS3
    *
    * @param function Function to be optimized (minimized).
    * @param stepSize Step size for each iteration.
-   * @param epsilon Value used to initialise the mean squared gradient parameter.
+   * @param epsilon Value used to initialise the mean squared gradient
+   *        parameter.
    * @param maxIterations Maximum number of iterations allowed (0 means no
    *        limit).
    * @param tolerance Maximum absolute tolerance to terminate algorithm.
@@ -81,14 +82,14 @@ class SMORMS3
    *        function is visited in linear order.
    */
   SMORMS3(DecomposableFunctionType& function,
-      const double stepSize = 0.001,
-      const double epsilon = 1e-16,
-      const size_t maxIterations = 100000,
-      const double tolerance = 1e-5,
-      const bool shuffle = true);
+          const double stepSize = 0.001,
+          const double epsilon = 1e-16,
+          const size_t maxIterations = 100000,
+          const double tolerance = 1e-5,
+          const bool shuffle = true);
 
   /**
-   * Optimize the given function using SMORMS3. The given starting point will 
+   * Optimize the given function using SMORMS3. The given starting point will
    * be modified to store the finishing point of the algorithm, and the final
    * objective value is returned.
    *
@@ -98,7 +99,10 @@ class SMORMS3
   double Optimize(arma::mat& iterate) { return optimizer.Optimize(iterate); }
 
   //! Get the instantiated function to be optimized.
-  const DecomposableFunctionType& Function() const { return optimizer.Function(); }
+  const DecomposableFunctionType& Function() const
+  {
+    return optimizer.Function();
+  }
   //! Modify the instantiated function.
   DecomposableFunctionType& Function() { return optimizer.Function(); }
 
diff --git a/src/mlpack/core/optimizers/smorms3/smorms3_update.hpp b/src/mlpack/core/optimizers/smorms3/smorms3_update.hpp
index fbc534926b..3cf35eb7df 100644
--- a/src/mlpack/core/optimizers/smorms3/smorms3_update.hpp
+++ b/src/mlpack/core/optimizers/smorms3/smorms3_update.hpp
@@ -26,10 +26,10 @@ namespace optimization {
  *
  * @code
  * @misc{Funk2015,
- *   author    = {Simon Funk},
- *   title     = {RMSprop loses to SMORMS3 - Beware the Epsilon!},
- *   year      = {2015}
- *   url       = {http://sifter.org/~simon/journal/20150420.html}
+ *   author = {Simon Funk},
+ *   title  = {RMSprop loses to SMORMS3 - Beware the Epsilon!},
+ *   year   = {2015}
+ *   url    = {http://sifter.org/~simon/journal/20150420.html}
  * }
  * @endcode
  */
@@ -40,23 +40,18 @@ class SMORMS3Update
   /**
    * Construct the SMORMS3 update policy with given epsilon parameter.
    *
-   * @param epsilon Value used to initialise the mean squared gradient parameter.
+   * @param epsilon Value used to initialise the mean squared gradient
+   *        parameter.
    */
-  SMORMS3Update(const double epsilon = 1e-16) :
-    epsilon(epsilon)
+  SMORMS3Update(const double epsilon = 1e-16) : epsilon(epsilon)
   { /* Do nothing. */ }
 
-  //! Get the value used to initialise the mean squared gradient parameter.
-  double Epsilon() const { return epsilon; }
-  //! Modify the value used to initialise the mean squared gradient parameter.
-  double& Epsilon() { return epsilon; }
-
   /**
    * The Initialize method is called by SGD::Optimize method with UpdatePolicy
    * SMORMS3Update before the start of the iteration update process.
    *
-   * @param rows number of rows in the gradient matrix.
-   * @param cols number of columns in the gradient matrix.
+   * @param rows Number of rows in the gradient matrix.
+   * @param cols Number of columns in the gradient matrix.
    */
   void Initialize(const size_t rows,
                   const size_t cols)
@@ -96,10 +91,16 @@ class SMORMS3Update
     mem %= (1 - x);
     mem += 1;
   }
+
+  //! Get the value used to initialise the mean squared gradient parameter.
+  double Epsilon() const { return epsilon; }
+  //! Modify the value used to initialise the mean squared gradient parameter.
+  double& Epsilon() { return epsilon; }
+
  private:
    //! The value used to initialise the mean squared gradient parameter.
    double epsilon;
-   
+
    // The parameters mem, g and g2.
    arma::mat mem, g, g2;
 };