Vector quantization

related topics
{math, number, function}
{math, energy, light}
{system, computer, user}
{rate, high, increase}
{household, population, female}
{group, member, jewish}
{service, military, aircraft}

Vector quantization is a classical quantization technique from signal processing which allows the modeling of probability density functions by the distribution of prototype vectors. It was originally used for data compression. It works by dividing a large set of points (vectors) into groups having approximately the same number of points closest to them. Each group is represented by its centroid point, as in k-means and some other clustering algorithms.

The density matching property of vector quantization is powerful, especially for identifying the density of large and high-dimensioned data. Since data points are represented by the index of their closest centroid, commonly occurring data have low error, and rare data high error. This is why VQ is suitable for lossy data compression. It can also be used for lossy data correction and density estimation.

Vector quantization is based on the competitive learning paradigm, so it is closely related to the self-organizing map model.



A simple training algorithm for vector quantization is:

A more sophisticated algorithm reduces the bias in the density matching estimation, and ensures that all points are used, by including an extra sensitivity parameter:

It is desirable to use a cooling schedule to produce convergence: see Simulated annealing.

The algorithm can be iteratively updated with 'live' data, rather than by picking random points from a data set, but this will introduce some bias if the data is temporally correlated over many samples.


Vector quantization is used for lossy data compression, lossy data correction and density estimation.

Lossy data correction, or prediction, is used to recover data missing from some dimensions. It is done by finding the nearest group with the data dimensions available, then predicting the result based on the values for the missing dimensions, assuming that they will have the same value as the group's centroid.

For density estimation, the area/volume that is closer to a particular centroid than to any other is inversely proportional to the density (due to the density matching property of the algorithm).

Use in data compression

Vector quantization, also called "block quantization" or "pattern matching quantization" is often used in lossy data compression. It works by encoding values from a multidimensional vector space into a finite set of values from a discrete subspace of lower dimension. A lower-space vector requires less storage space, so the data is compressed. Due to the density matching property of vector quantization, the compressed data have errors that are inversely proportional to their density.

Full article ▸

related documents
Order of magnitude
Harmonic function
Examples of differential equations
Periodic function
No cloning theorem
Bridge pattern
Cauchy distribution
Range encoding
Whittaker–Shannon interpolation formula
Reverse Polish notation
Greedy algorithm
Heaviside step function
Linear congruential generator
Twin prime conjecture
Separated sets
Magma (algebra)
Logarithmic integral function
Topological ring
Goldbach's weak conjecture
Kernel (category theory)
Intersection (set theory)
Graded algebra
Euler's criterion
Lipschitz continuity
Convex hull
Complement (set theory)
Hidden Markov model