Finite-Sample Risk Bounds for Maximum Likelihood Estimation With Arbitrary Penalties

Abstract

The minimum description length two-part coding <italic>index of resolvability</italic> provides a finite-sample upper bound on the statistical risk of penalized likelihood estimators over countable models. However, the bound does not apply to unpenalized maximum likelihood estimation or procedures with exceedingly small penalties. In this paper, we point… (More)
DOI: 10.1109/TIT.2017.2789214

Topics

  • Presentations referencing similar topics