zero tolerance added for whitening in PCA

shogun-toolbox · Mar 26, 2014 · 0562e62 · 0562e62
1 parent e20e711
commit 0562e62
Show file tree

Hide file tree

Showing 2 changed files with 59 additions and 3 deletions.
diff --git a/src/shogun/preprocessor/PCA.cpp b/src/shogun/preprocessor/PCA.cpp
@@ -57,7 +57,8 @@ void CPCA::init()
 	m_mode = FIXED_NUMBER;
 	m_thresh = 1e-6;
 	m_mem_mode = MEM_REALLOCATE;
-	m_method = AUTO;	
+	m_method = AUTO;
+	m_eigenvalue_zero_tolerance=1e-15;	
 
 	SG_ADD(&m_transformation_matrix, "transformation_matrix",
 	    "Transformation matrix (Eigenvectors of covariance matrix).",
@@ -75,6 +76,8 @@ void CPCA::init()
 		"Memory mode (in-place or reallocation).", MS_NOT_AVAILABLE);
 	SG_ADD((machine_int_t*) &m_method, "m_method", 
 		"Method used for PCA calculation", MS_NOT_AVAILABLE);
+	SG_ADD(&m_eigenvalue_zero_tolerance, "eigenvalue_zero_tolerance", "zero tolerance"
+	" for determining zero eigenvalues during whitening to avoid numerical issues", MS_NOT_AVAILABLE);
 }
 
 CPCA::~CPCA()
@@ -171,8 +174,22 @@ bool CPCA::init(CFeatures* features)
 			if (m_whitening)
 			{
 				for (int32_t i=0; i<num_dim; i++)
+				{
+					if (CMath::fequals_abs<float64_t>(0.0, eigenValues[i+max_dim_allowed-num_dim], 
+											m_eigenvalue_zero_tolerance))
+					{
+						SG_WARNING("Covariance matrix has almost zero Eigenvalue (ie "
+							"Eigenvalue within a tolerance of %E around 0) at "
+							"dimension %d. Consider reducing its dimension.", 
+							m_eigenvalue_zero_tolerance, i+max_dim_allowed-num_dim+1)
+
+						transformMatrix.col(i) = MatrixXd::Zero(num_features,1);
+						continue;
+					}
+
 					transformMatrix.col(i) /= 
-					sqrt(eigenValues[i+max_dim_allowed-num_dim]*(num_vectors-1)+1e-15);
+					sqrt(eigenValues[i+max_dim_allowed-num_dim]*(num_vectors-1));
+				}
 			}
 		}
 
@@ -226,7 +243,21 @@ bool CPCA::init(CFeatures* features)
 			if (m_whitening)
 			{
 				for (int32_t i=0; i<num_dim; i++)
-					transformMatrix.col(i) /= sqrt(eigenValues[i]*(num_vectors-1)+1e-15);
+				{
+					if (CMath::fequals_abs<float64_t>(0.0, eigenValues[i], 
+								m_eigenvalue_zero_tolerance))
+					{
+						SG_WARNING("Covariance matrix has almost zero Eigenvalue (ie "
+							"Eigenvalue within a tolerance of %E around 0) at "
+							"dimension %d. Consider reducing its dimension.", 
+							m_eigenvalue_zero_tolerance, i+1)
+
+						transformMatrix.col(i) = MatrixXd::Zero(num_features,1);
+						continue;
+					}
+
+					transformMatrix.col(i) /= sqrt(eigenValues[i]*(num_vectors-1));
+				}
 			}
 		}
 
@@ -343,4 +374,14 @@ void CPCA::set_memory_mode(EPCAMemoryMode e)
 	m_mem_mode = e;
 }
 
+void CPCA::set_eigenvalue_zero_tolerance(float64_t eigenvalue_zero_tolerance)
+{
+	m_eigenvalue_zero_tolerance = eigenvalue_zero_tolerance;
+}
+
+float64_t CPCA::get_eigenvalue_zero_tolerance() const
+{
+	return m_eigenvalue_zero_tolerance;
+}
+
 #endif // HAVE_EIGEN3
diff --git a/src/shogun/preprocessor/PCA.h b/src/shogun/preprocessor/PCA.h
@@ -185,6 +185,16 @@ class CPCA: public CDimensionReductionPreprocessor
 		 */
 		void set_memory_mode(EPCAMemoryMode e);
 
+		/** set zero tolerance of eigenvalues during data whitening
+		 * @param eigenvalue_zero_tolerance zero tolerance value
+		 */
+		void set_eigenvalue_zero_tolerance(float64_t eigenvalue_zero_tolerance=1e-15);
+
+		/** get zero tolerance of eigenvalues during data whitening
+		 * @return zero tolerance value
+		 */
+		float64_t get_eigenvalue_zero_tolerance() const;
+
 	protected:
 
 		void init();
@@ -213,6 +223,11 @@ class CPCA: public CDimensionReductionPreprocessor
 		EPCAMemoryMode m_mem_mode;
 		/** PCA method */
 		EPCAMethod m_method;
+		/** eigenvalues within zero tolerance
+		 * region are considered 0 while
+		 * whitening to tackle numerical issues
+		 */
+		float64_t m_eigenvalue_zero_tolerance;
 };
 }
 #endif // HAVE_EIGEN3