diff --git a/src/mlpack/methods/lars/lars.cpp b/src/mlpack/methods/lars/lars.cpp
index 848f9ebb67..df0ce98f45 100644
--- a/src/mlpack/methods/lars/lars.cpp
+++ b/src/mlpack/methods/lars/lars.cpp
@@ -68,6 +68,120 @@ LARS::LARS(const arma::mat& data,
   Train(data, responses, transposeData);
 }
 
+// Copy Constructor.
+LARS::LARS(const LARS& other) :
+    matGramInternal(other.matGramInternal),
+    matGram(&matGramInternal),
+    matUtriCholFactor(other.matUtriCholFactor),
+    useCholesky(other.useCholesky),
+    lasso(other.lasso),
+    lambda1(other.lambda1),
+    lambda2(other.lambda2),
+    elasticNet(other.elasticNet),
+    tolerance(other.tolerance),
+    betaPath(other.betaPath),
+    lambdaPath(other.lambdaPath),
+    activeSet(other.activeSet),
+    isActive(other.isActive),
+    ignoreSet(other.ignoreSet),
+    isIgnored(other.isIgnored)
+{
+  // Nothing to do here.
+}
+
+// Move constructor.
+LARS::LARS(LARS&& other) :
+    matGramInternal(std::move(other.matGramInternal)),
+    matGram(other.matGram),
+    matUtriCholFactor(std::move(other.matUtriCholFactor)),
+    useCholesky(other.useCholesky),
+    lasso(other.lasso),
+    lambda1(other.lambda1),
+    lambda2(other.lambda2),
+    elasticNet(other.elasticNet),
+    tolerance(other.tolerance),
+    betaPath(std::move(other.betaPath)),
+    lambdaPath(std::move(other.lambdaPath)),
+    activeSet(std::move(other.activeSet)),
+    isActive(std::move(other.isActive)),
+    ignoreSet(std::move(other.ignoreSet)),
+    isIgnored(std::move(other.isIgnored))
+{
+  // Clean the other object to prevent to objects pointing
+  // at the memory location.
+  if (other.matGram)
+    delete other.matGram;
+
+  other.matGram = new arma::mat(other.matGramInternal);
+  other.lambda1 = 0.0;
+  other.lambda2 = 0.0;
+}
+
+// Copy operator.
+LARS& LARS::operator=(const LARS& other)
+{
+  if (&other == this)
+    return *this;
+
+  // Clean the memory first.
+  if (matGram)
+    delete matGram;
+
+  matGramInternal = other.matGramInternal;
+  matGram = &matGramInternal;
+  matUtriCholFactor = other.matUtriCholFactor;
+  useCholesky = other.useCholesky;
+  lasso = other.lasso;
+  lambda1 = other.lambda1;
+  lambda2 = other.lambda2;
+  elasticNet = other.elasticNet;
+  tolerance = other.tolerance;
+  betaPath = other.betaPath;
+  lambdaPath = other.lambdaPath;
+  activeSet = other.activeSet;
+  isActive = other.isActive;
+  ignoreSet = other.ignoreSet;
+  isIgnored = other.isIgnored;
+  return *this;
+}
+
+// Move Operator.
+LARS& LARS::operator=(LARS&& other)
+{
+  if (&other == this)
+    return *this;
+
+  // Clean the memory first.
+  if (matGram)
+    delete matGram;
+
+  matGramInternal = std::move(other.matGramInternal);
+  matGram = other.matGram;
+  matUtriCholFactor = std::move(other.matUtriCholFactor);
+  useCholesky = other.useCholesky;
+  lasso = other.lasso;
+  lambda1 = other.lambda1;
+  lambda2 = other.lambda2;
+  elasticNet = other.elasticNet;
+  tolerance = other.tolerance;
+  betaPath = std::move(other.betaPath);
+  lambdaPath = std::move(other.lambdaPath);
+  activeSet = std::move(other.activeSet);
+  isActive = std::move(other.isActive);
+  ignoreSet = std::move(other.ignoreSet);
+  isIgnored = std::move(other.isIgnored);
+
+  // Clean the other object to prevent to objects pointing
+  // at the memory location.
+  if (other.matGram)
+    delete other.matGram;
+
+  other.matGram = new arma::mat(other.matGramInternal);
+  other.lambda1 = 0.0;
+  other.lambda2 = 0.0;
+  return *this;
+}
+
 double LARS::Train(const arma::mat& matX,
                    const arma::rowvec& y,
                    arma::vec& beta,
diff --git a/src/mlpack/methods/lars/lars.hpp b/src/mlpack/methods/lars/lars.hpp
index 9d7aa24ada..da3de1fdfd 100644
--- a/src/mlpack/methods/lars/lars.hpp
+++ b/src/mlpack/methods/lars/lars.hpp
@@ -170,6 +170,34 @@ class LARS
        const double lambda2 = 0.0,
        const double tolerance = 1e-16);
 
+  /**
+   * Construct the LARS object by copying the given LARS object.
+   *
+   * @param other LARS object to copy.
+   */
+  LARS(const LARS& other);
+
+  /**
+   * Construct the LARS object by taking ownership of the given LARS object.
+   *
+   * @param other LARS object to take ownership of.
+   */
+  LARS(LARS&& other);
+
+  /**
+   * Copy the given LARS object.
+   *
+   * @param other LARS object to copy.
+   */
+  LARS &operator=(const LARS& other);
+
+  /**
+   * Take ownership of the given LARS object.
+   *
+   * @param other LARS object to take ownership of.
+   */
+  LARS &operator=(LARS&& other);
+
   /**
    * Run LARS.  The input matrix (like all mlpack matrices) should be
    * column-major -- each column is an observation and each row is a dimension.
diff --git a/src/mlpack/tests/lars_test.cpp b/src/mlpack/tests/lars_test.cpp
index 6b7edc267e..f2eb89b230 100644
--- a/src/mlpack/tests/lars_test.cpp
+++ b/src/mlpack/tests/lars_test.cpp
@@ -421,4 +421,36 @@ BOOST_AUTO_TEST_CASE(LARSTestComputeError)
   BOOST_REQUIRE_EQUAL(cost == train1, true);
 }
 
+BOOST_AUTO_TEST_CASE(LARSCopyConstructorTest)
+{
+  arma::mat features, Y;
+  arma::rowvec targets;
+  data::Load("lars_dependent_x.csv", features);
+  data::Load("lars_dependent_y.csv", Y);
+  targets = Y.row(0);
+  mlpack::regression::LARS* glm1 = new mlpack::regression::LARS(false, .1, .1);
+  arma::rowvec predictions, predictionsFromCopiedModel;
+  std::vector<mlpack::regression::LARS> models;
+  glm1->Train(features, targets);
+  glm1->Predict(features, predictions);
+  models.emplace_back(*glm1);
+  delete glm1; // Free LARS internal memory.
+  models[0].Predict(features, predictionsFromCopiedModel);
+  CheckMatrices(predictions, predictionsFromCopiedModel);
+  // Check if we can train the model again.
+  BOOST_REQUIRE_NO_THROW(models[0].Train(features, targets));
+
+  // Check for object.
+  mlpack::regression::LARS glm2(false, 0.1, 0.1);
+  models.emplace_back(glm2);
+  BOOST_REQUIRE_NO_THROW(glm2.Train(features, targets));
+  BOOST_REQUIRE_NO_THROW(models[1].Train(features, targets));
+
+  // Check assignment operator.
+  mlpack::regression::LARS glm3 = glm2;
+  models[1].Predict(features, predictions);
+  glm3.Predict(features, predictionsFromCopiedModel);
+  CheckMatrices(predictions, predictionsFromCopiedModel);
+}
+
 BOOST_AUTO_TEST_SUITE_END();