diff --git a/docs/changes.tex b/docs/changes.tex
index 5e5bf44e4..cd41fd3f5 100644
--- a/docs/changes.tex
+++ b/docs/changes.tex
@@ -12,6 +12,8 @@
     TolerantLossFunction} and \texttt{ComposedLossFunction}. (James Roseborough).
 \item New \texttt{DENSE\_NORMAL\_CHOLESKY} linear solver, which uses Eigen's
   LDLT factorization on the normal equations.
+\item Cached symbolic factorization when using \texttt{CXSparse}.
+  (Petter Strandark)
 \item The traditional Dogleg solver now uses an elliptical trust
   region (Markus Moll)
 \item Support for returning initial and final gradients \& Jacobians.
@@ -38,7 +40,7 @@
 \begin{itemize}
 \item Do not link to \texttt{libgomp} when building on
   windows. (Petter Strandmark)
-\item Include \texttt{gflags.h} in \texttt{test_utils.cc}. (Petter
+\item Include \texttt{gflags.h} in \texttt{test\_utils.cc}. (Petter
   Strandmark)
 \item Use standard random number generation routines. (Petter Strandmark)
 \item \texttt{TrustRegionMinimizer} does not implicitly negate the
diff --git a/internal/ceres/cxsparse.cc b/internal/ceres/cxsparse.cc
index f54d24ffd..ca36ce076 100644
--- a/internal/ceres/cxsparse.cc
+++ b/internal/ceres/cxsparse.cc
@@ -48,7 +48,9 @@ CXSparse::~CXSparse() {
   }
 }
 
-bool CXSparse::SolveCholesky(cs_di* A, cs_dis* factor, double* b) {
+bool CXSparse::SolveCholesky(cs_di* A,
+                             cs_dis* symbolic_factorization,
+                             double* b) {
   // Make sure we have enough scratch space available.
   if (scratch_size_ < A->n) {
     if (scratch_size_ > 0) {
@@ -58,28 +60,29 @@ bool CXSparse::SolveCholesky(cs_di* A, cs_dis* factor, double* b) {
   }
 
   // Solve using Cholesky factorization
-  csn* N = cs_chol(A, factor);
-  if (N == NULL) {
+  csn* numeric_factorization = cs_chol(A, symbolic_factorization);
+  if (numeric_factorization == NULL) {
     LOG(WARNING) << "Cholesky factorization failed.";
     return false;
   }
 
   // When the Cholesky factorization succeeded, these methods are guaranteed to
-  // succeed as well. In the comments below, "x" refers to the scratch space.
+  // succeeded as well. In the comments below, "x" refers to the scratch space.
+  //
   // Set x = P * b.
-  cs_ipvec(factor->pinv, b, scratch_, A->n);
+  cs_ipvec(symbolic_factorization->pinv, b, scratch_, A->n);
 
   // Set x = L \ x.
-  cs_lsolve(N->L, scratch_);
+  cs_lsolve(numeric_factorization->L, scratch_);
 
   // Set x = L' \ x.
-  cs_ltsolve(N->L, scratch_);
+  cs_ltsolve(numeric_factorization->L, scratch_);
 
   // Set b = P' * x.
-  cs_pvec(factor->pinv, scratch_, b, A->n);
+  cs_pvec(symbolic_factorization->pinv, scratch_, b, A->n);
 
   // Free Cholesky factorization.
-  cs_nfree(N);
+  cs_nfree(numeric_factorization);
   return true;
 }
 
diff --git a/internal/ceres/cxsparse.h b/internal/ceres/cxsparse.h
index a1265103a..d3b64fcd1 100644
--- a/internal/ceres/cxsparse.h
+++ b/internal/ceres/cxsparse.h
@@ -51,13 +51,13 @@ class CXSparse {
   ~CXSparse();
 
   // Solves a symmetric linear system A * x = b using Cholesky factorization.
-  //  A      - The system matrix.
-  //  factor - The symbolic factorization of A. This is obtained from
-  //           AnalyzeCholesky.
-  //  b      - The right hand size of the linear equation. This array will also
-  //           recieve the solution.
+  //  A                      - The system matrix.
+  //  symbolic_factorization - The symbolic factorization of A. This is obtained
+  //                           from AnalyzeCholesky.
+  //  b                      - The right hand size of the linear equation. This
+  //                           array will also recieve the solution.
   // Returns false if Cholesky factorization of A fails.
-  bool SolveCholesky(cs_di* A, cs_dis* factor, double* b);
+  bool SolveCholesky(cs_di* A, cs_dis* symbolic_factorization, double* b);
 
   // Creates a sparse matrix from a compressed-column form. No memory is
   // allocated or copied; the structure A is filled out with info from the