The LSHSearch class – This class builds a hash on the reference set and uses this hash to compute the distance-approximate nearest-neighbors of the given queries.
More...
|
| LSHSearch (const arma::mat &referenceSet, const arma::mat &querySet, const size_t numProj, const size_t numTables, const double hashWidth=0.0, const size_t secondHashSize=99901, const size_t bucketSize=500) |
| This function initializes the LSH class. More...
|
|
| LSHSearch (const arma::mat &referenceSet, const size_t numProj, const size_t numTables, const double hashWidth=0.0, const size_t secondHashSize=99901, const size_t bucketSize=500) |
| This function initializes the LSH class. More...
|
|
void | Search (const size_t k, arma::Mat< size_t > &resultingNeighbors, arma::mat &distances, const size_t numTablesToSearch=0) |
| Compute the nearest neighbors and store the output in the given matrices. More...
|
|
std::string | ToString () const |
|
|
double | BaseCase (const size_t queryIndex, const size_t referenceIndex) |
| This is a helper function that computes the distance of the query to the neighbor candidates and appropriately stores the best 'k' candidates. More...
|
|
void | BuildHash () |
| This function builds a hash table with two levels of hashing as presented in the paper. More...
|
|
void | InsertNeighbor (const size_t queryIndex, const size_t pos, const size_t neighbor, const double distance) |
| This is a helper function that efficiently inserts better neighbor candidates into an existing set of neighbor candidates. More...
|
|
void | ReturnIndicesFromTable (const size_t queryIndex, arma::uvec &referenceIndices, size_t numTablesToSearch) |
| This function takes a query and hashes it into each of the hash tables to get keys for the query and then the key is hashed to a bucket of the second hash table and all the points (if any) in those buckets are collected as the potential neighbor candidates. More...
|
|
template<typename SortPolicy = NearestNeighborSort>
class mlpack::neighbor::LSHSearch< SortPolicy >
The LSHSearch class – This class builds a hash on the reference set and uses this hash to compute the distance-approximate nearest-neighbors of the given queries.
- Template Parameters
-
Definition at line 51 of file lsh_search.hpp.
template<typename SortPolicy = NearestNeighborSort>
mlpack::neighbor::LSHSearch< SortPolicy >::LSHSearch |
( |
const arma::mat & |
referenceSet, |
|
|
const arma::mat & |
querySet, |
|
|
const size_t |
numProj, |
|
|
const size_t |
numTables, |
|
|
const double |
hashWidth = 0.0 , |
|
|
const size_t |
secondHashSize = 99901 , |
|
|
const size_t |
bucketSize = 500 |
|
) |
| |
This function initializes the LSH class.
It builds the hash on the reference set with 2-stable distributions. See the individual functions performing the hashing for details on how the hashing is done.
- Parameters
-
referenceSet | Set of reference points. |
querySet | Set of query points. |
numProj | Number of projections in each hash table (anything between 10-50 might be a decent choice). |
numTables | Total number of hash tables (anything between 10-20 should suffice). |
hashWidth | The width of hash for every table. If 0 (the default) is provided, then the hash width is automatically obtained by computing the average pairwise distance of 25 pairs. This should be a reasonable upper bound on the nearest-neighbor distance in general. |
secondHashSize | The size of the second hash table. This should be a large prime number. |
bucketSize | The size of the bucket in the second hash table. This is the maximum number of points that can be hashed into single bucket. Default values are already provided here. |
template<typename SortPolicy = NearestNeighborSort>
mlpack::neighbor::LSHSearch< SortPolicy >::LSHSearch |
( |
const arma::mat & |
referenceSet, |
|
|
const size_t |
numProj, |
|
|
const size_t |
numTables, |
|
|
const double |
hashWidth = 0.0 , |
|
|
const size_t |
secondHashSize = 99901 , |
|
|
const size_t |
bucketSize = 500 |
|
) |
| |
This function initializes the LSH class.
It builds the hash on the reference set with 2-stable distributions. See the individual functions performing the hashing for details on how the hashing is done.
- Parameters
-
referenceSet | Set of reference points and the set of queries. |
numProj | Number of projections in each hash table (anything between 10-50 might be a decent choice). |
numTables | Total number of hash tables (anything between 10-20 should suffice). |
hashWidth | The width of hash for every table. If 0 (the default) is provided, then the hash width is automatically obtained by computing the average pairwise distance of 25 pairs. This should be a reasonable upper bound on the nearest-neighbor distance in general. |
secondHashSize | The size of the second hash table. This should be a large prime number. |
bucketSize | The size of the bucket in the second hash table. This is the maximum number of points that can be hashed into single bucket. Default values are already provided here. |
template<typename SortPolicy = NearestNeighborSort>
This is a helper function that computes the distance of the query to the neighbor candidates and appropriately stores the best 'k' candidates.
- Parameters
-
queryIndex | The index of the query in question |
referenceIndex | The index of the neighbor candidate in question |
template<typename SortPolicy = NearestNeighborSort>
This function builds a hash table with two levels of hashing as presented in the paper.
This function first hashes the points with 'numProj' random projections to a single hash table creating (key, point ID) pairs where the key is a 'numProj'-dimensional integer vector.
Then each key in this hash table is hashed into a second hash table using a standard hash.
This function does not have any parameters and relies on parameters which are private members of this class, initialized during the class initialization.
template<typename SortPolicy = NearestNeighborSort>
void mlpack::neighbor::LSHSearch< SortPolicy >::InsertNeighbor |
( |
const size_t |
queryIndex, |
|
|
const size_t |
pos, |
|
|
const size_t |
neighbor, |
|
|
const double |
distance |
|
) |
| |
|
private |
This is a helper function that efficiently inserts better neighbor candidates into an existing set of neighbor candidates.
This function is only called by the 'BaseCase' function.
- Parameters
-
queryIndex | This is the index of the query being processed currently |
pos | The position of the neighbor candidate in the current list of neighbor candidates. |
neighbor | The neighbor candidate that is being inserted into the list of the best 'k' candidates for the query in question. |
distance | The distance of the query to the neighbor candidate. |
template<typename SortPolicy = NearestNeighborSort>
void mlpack::neighbor::LSHSearch< SortPolicy >::ReturnIndicesFromTable |
( |
const size_t |
queryIndex, |
|
|
arma::uvec & |
referenceIndices, |
|
|
size_t |
numTablesToSearch |
|
) |
| |
|
private |
This function takes a query and hashes it into each of the hash tables to get keys for the query and then the key is hashed to a bucket of the second hash table and all the points (if any) in those buckets are collected as the potential neighbor candidates.
- Parameters
-
queryIndex | The index of the query currently being processed. |
referenceIndices | The list of neighbor candidates obtained from hashing the query into all the hash tables and eventually into multiple buckets of the second hash table. |
template<typename SortPolicy = NearestNeighborSort>
void mlpack::neighbor::LSHSearch< SortPolicy >::Search |
( |
const size_t |
k, |
|
|
arma::Mat< size_t > & |
resultingNeighbors, |
|
|
arma::mat & |
distances, |
|
|
const size_t |
numTablesToSearch = 0 |
|
) |
| |
Compute the nearest neighbors and store the output in the given matrices.
The matrices will be set to the size of n columns by k rows, where n is the number of points in the query dataset and k is the number of neighbors being searched for.
- Parameters
-
k | Number of neighbors to search for. |
resultingNeighbors | Matrix storing lists of neighbors for each query point. |
distances | Matrix storing distances of neighbors for each query point. |
numTablesToSearch | This parameter allows the user to have control over the number of hash tables to be searched. This allows the user to pick the number of tables it can afford for the time available without having to build hashing for every table size. By default, this is set to zero in which case all tables are considered. |
template<typename SortPolicy = NearestNeighborSort>
template<typename SortPolicy = NearestNeighborSort>
The number of elements present in each hash bucket; should be secondHashSize.
Definition at line 229 of file lsh_search.hpp.
template<typename SortPolicy = NearestNeighborSort>
For a particular hash value, points to the row in secondHashTable corresponding to this value.
Should be secondHashSize.
Definition at line 233 of file lsh_search.hpp.
template<typename SortPolicy = NearestNeighborSort>
template<typename SortPolicy = NearestNeighborSort>
The pointer to the nearest neighbor distances.
Definition at line 236 of file lsh_search.hpp.
template<typename SortPolicy = NearestNeighborSort>
template<typename SortPolicy = NearestNeighborSort>
template<typename SortPolicy = NearestNeighborSort>
The pointer to the nearest neighbor indices.
Definition at line 239 of file lsh_search.hpp.
template<typename SortPolicy = NearestNeighborSort>
template<typename SortPolicy = NearestNeighborSort>
template<typename SortPolicy = NearestNeighborSort>
The list of the offset 'b' for each of the projection for each table.
Definition at line 207 of file lsh_search.hpp.
template<typename SortPolicy = NearestNeighborSort>
The std::vector containing the projection matrix of each table.
Definition at line 204 of file lsh_search.hpp.
template<typename SortPolicy = NearestNeighborSort>
template<typename SortPolicy = NearestNeighborSort>
template<typename SortPolicy = NearestNeighborSort>
The big prime representing the size of the second hash.
Definition at line 213 of file lsh_search.hpp.
template<typename SortPolicy = NearestNeighborSort>
The final hash table; should be (< secondHashSize) x bucketSize.
Definition at line 225 of file lsh_search.hpp.
template<typename SortPolicy = NearestNeighborSort>
The documentation for this class was generated from the following file: