Fast rates for empirical vector quantization

Details Fast rates for empirical vector quantization Fast rates for empirical vector quantization

2012-01-29

arxiv.org/abs/1201.6052v1

Mathematics

Statistics Theory

18 pages

Scientific paper

We consider the rate of convergence of the expected loss of empirically optimal vector quantizers. Earlier results show that the mean-squared expected distortion for any fixed distribution supported on a bounded set and satisfying some regularity conditions decreases at the rate O(log n/n). We prove that this rate is actually O(1/n). Although these conditions are hard to check, we show that well-polarized distributions with continuous densities supported on a bounded set are included in the scope of this result.

Affiliated with

Also associated with

No associations

Rating

Fast rates for empirical vector quantization does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Fast rates for empirical vector quantization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Fast rates for empirical vector quantization will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-379271