Vector quantization and signal compression
Vector quantization and signal compression
Methods of mathematical economics linear and nonlinear programming, fixed-point theorems
Methods of mathematical economics linear and nonlinear programming, fixed-point theorems
The Canonical Distortion Measure for Vector Quantization and Function Approximation
ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
| Hi-index | 0.08 |
Discrete functions over a continuous domain are approximated by discrete functions with fewer levels. These quantizations are endowed with different types of constraints such as monotonicity and variational constraints. Quantization functions exactly or approximately minimize the squared error to a given discrete function. Exact algorithms are derived from dynamic programming with finite horizon. All algorithms have polynomial run time.