On the Convergence of MDL Density Estimation

Tong Zhang

Abstract

We present a general information exponential inequality that measures the statistical complexity of some deterministic and randomized density estimators. Using this inequality, we are able to improve classical results concerning the convergence of two-part code MDL in [1]. Moreover, we are able to derive clean finite-sample convergence bounds that are not obtainable using previous approaches.
BibTeX
@inproceedings{zhang2004convergence,
  author = {Tong Zhang},
  title = {{On the Convergence of MDL Density Estimation}},
  booktitle = {Conference on Learning Theory},
  year = {2004},
  doi = {10.1007/978-3-540-27819-1\_22},
}

Loading related content...

Figure