Paper #198

Título:

The minimax distortion redundancy in empirical quantizer design

Autores:

Peter Bartlett, Tamas Linder y Gábor Lugosi

Data:

Enero 1997

Resumen:

We obtain minimax lower and upper bounds for the expected distortion redundancy of empirically designed vector quantizers. We show that the mean squared distortion of a vector quantizer designed from $n$ i.i.d. data points using any design algorithm is at least $\Omega (n^{-1/2})$ away from the optimal distortion for some distribution on a bounded subset of ${\cal R}^d$. Together with existing upper bounds this result shows that the minimax distortion redundancy for empirical quantizer design, as a function of the size of the training data, is asymptotically on the order of $n^{1/2}$. We also derive a new upper bound for the performance of the empirically optimal quantizer.

Palabras clave:

Estimation, hypothesis testing, statistical decision theory: operations research

Códigos JEL:

C13, C14

Área de investigación:

Estadística, Econometría y Métodos Cuantitativos

Publicado en:

IEEE Transactions on Information Theory, 44, (1998), pp. 1802-1813

Descargar el paper en formato PDF