Limit theorems for random normalized distortion
Cohort, Pierre
Ann. Appl. Probab., Tome 14 (2004) no. 1, p. 118-143 / Harvested from Project Euclid
We present some convergence results about the distortion $\mathcal{D}_{\mu,n,r}^{\nu}$ related to the Voronoï vector quantization of a $\mu$-distributed random variable using $n$ i.i.d. $\nu$-distributed codes. A weak law of large numbers for $n^{r/d}\mathcal{D}_{\mu,n,r}^{\nu}$ is derived essentially under a $\mu$-integrability condition on a negative power of a $\delta$-lower Radon--Nikodym derivative of $\nu$. Assuming in addition that the probability measure $\mu$ has a bounded $\varepsilon$-potential, we obtain a strong law of large numbers for $n^{r/d} \mathcal{D}_{\mu,n,r}^{\nu}$. In particular, we show that the random distortion and the optimal distortion vanish almost surely at the same rate. In the one-dimensional setting ($d=1$), we derive a central limit theorem for $n^{r}\mathcal{D}_{\mu,n,r}^{\nu}$. The related limiting variance is explicitly computed.
Publié le : 2004-02-14
Classification:  Quantization,  distortion,  law of large numbers,  central limit theorem,  60F25,  60F15,  60F05,  94A29
@article{1075828049,
     author = {Cohort, Pierre},
     title = {Limit theorems for random normalized distortion},
     journal = {Ann. Appl. Probab.},
     volume = {14},
     number = {1},
     year = {2004},
     pages = { 118-143},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1075828049}
}
Cohort, Pierre. Limit theorems for random normalized distortion. Ann. Appl. Probab., Tome 14 (2004) no. 1, pp.  118-143. http://gdmltest.u-ga.fr/item/1075828049/