This is kind of theoretical sounding but it may be relevant to the question
of validation which was recently raised.
Frank
---
Frank C. Wimberly 505 995-8715 or 505
670-9918 (mobile)
140 Calle Ojo Feliz
[hidden email]
or
[hidden email]
Santa Fe, NM 87505
http://www.andrew.cmu.edu/user/wimberly----- Original Message -----
From: Sharon Woodside
To:
[hidden email]
Sent: Monday, June 09, 2003 8:28 AM
Subject: CALD Seminar: Peter Grunwald
CALD Seminar:
June 11, 2003
Newell-Simon 3305
3:00pm-4:30pm
Speaker: Peter Grunwald, CWI
Title: Introduction to *Modern* MDL
Abstract:
The Minimum Description Length (MDL) Principle is an information-theoretic
method for statistical inference, in particular model selection. In recent
years, particularly since 1995, researchers have made significant
theoretical advances concerning MDL. In this talk we aim to present these
results to a wider audience. In its modern guise, MDL is based on the
concept of a `universal model'. We explain this concept at length. We show
that previous versions of MDL (based on so-called two-part codes), Bayesian
model selection and predictive validation (a form of cross-validation) can
all be interpreted as approximations to model selection based on `universal
models'. Modern MDL prescribes the use of a certain `optimal' universal
model, the so-called `normalized maximum likelihood model' or `Shtarkov
distribution'. This is related to (yet different from) Bayesian model
selection with non-informative priors. It leads to a penalization of
`complex' models that can be given an intuitive differential-geometric
interpretation. Roughly speaking, the complexity of a parametric model is
directly related to the number of distinguishable probability distributions
that it contains.
http://homepages.cwi.nl/~pdg/
Locked
