Caesar AI Atlas

Sparsity

Caesar AI Atlas Definition

Sparsity is the proportion of zero or empty entries in a vector, matrix, feature representation, or model parameter set. High sparsity can reduce storage and computation but may require specialized representations or algorithms.

Other Definitions

Sparsity Source

The number of elements set to zero (or null) in a vector or matrix divided by the total number of entries in that vector or matrix. For example, consider a 100-element matrix in which 98 cells contain zero. The calculation of sparsity is as follows: Feature sparsity refers to the sparsity of a feature vector; model sparsity refers to the sparsity of the model weights.

Related Terms