Implementation of Multiprobe LSH

src/mlpack/methods/lsh/lsh_search.hpp

@@ -359,10 +359,10 @@ class LSHSearch
    * @param additionalProbingBins matrix. Each column will hold one additional
    * bin.
   */
-  void GetAdditionalProbingBins(const arma::vec &queryCode,
-                            const arma::vec &queryCodeNotFloored,
+  void GetAdditionalProbingBins(const arma::vec& queryCode,
+                            const arma::vec& queryCodeNotFloored,
                             const size_t T,
-                            arma::mat &additionalProbingBins) const;
+                            arma::mat& additionalProbingBins) const;
 
   //! Reference dataset.
   const arma::mat* referenceSet;

src/mlpack/methods/lsh/lsh_search_impl.hpp

@@ -402,20 +402,22 @@ inline bool perturbationValid(const std::vector<size_t>& A,
 }
 */
 
-//Returns the score of a perturbation vector generated by perturbation set A.
-//The score of a pertubation set (vector) is the sum of scores of the
-//participating actions.
+// Returns the score of a perturbation vector generated by perturbation set A.
+// The score of a pertubation set (vector) is the sum of scores of the
+// participating actions.
 inline double perturbationScore(const std::vector<bool>& A,
                                 const arma::vec& scores)
 {
   double score = 0.0;
   for (size_t i = 0; i < A.size(); ++i)
-    score += A[i] ? scores(i) : 0; //add scores of non-zero indices
+    if (A[i])
+      score += scores(i) // add scores of non-zero indices
   return score;
 }
 
 // Inline function used by GetAdditionalProbingBins. The vector shift operation
 // replaces the largest element of a vector A with (largest element) + 1.
+// Returns true if resulting vector is valid, otherwise false.
 inline bool perturbationShift(std::vector<bool>& A)
 {
   size_t maxPos = 0;
@@ -434,18 +436,19 @@ inline bool perturbationShift(std::vector<bool>& A)
 
 // Inline function used by GetAdditionalProbingBins. The vector expansion
 // operation adds the element [1 + (largest_element)] to a vector A, where
-// largest_element is the largest element of A.
+// largest_element is the largest element of A. Returns true if resulting vector
+// is valid, otherwise false.
 inline bool perturbationExpand(std::vector<bool>& A)
 {
   // Find the last '1' in A
   size_t maxPos = 0;
   for (size_t i = 0; i < A.size(); ++i)
-    if (A[i]) //marked true
+    if (A[i]) // marked true
       maxPos = i;
 
   if ( maxPos + 1 < A.size()) // otherwise, this is an invalid vector
   {
-    A[maxPos+1] = 1;
+    A[maxPos + 1] = 1;
     return true;
   }
   return false;
@@ -458,16 +461,12 @@ inline bool perturbationExpand(std::vector<bool>& A)
 inline bool perturbationValid(const std::vector<bool>& A,
                               const size_t numProj)
 {
-  // Stack allocation and initialization to 0 (bool check[numProj] = {0}) made
-  // some compilers complain, and std::vector might even be compressed (depends
-  // on implementation) so this saves some space.
+  // Use check to mark dimensions we have seen before in A. If a dimension is
+  // seen twice (or more), A is not a valid perturbation.
   std::vector<bool> check(numProj);
 
   if (A.size() > 2 * numProj)
-  {
-    Log::Assert(1 == 2);
-    return false; // This should never happen
-  }
+    return false; // This should never happen.
 
   // Check that we only see each dimension once. If not, vector is not valid.
   for (size_t i = 0; i < A.size(); ++i)