Home > research resources > Nonparametric Bayesian

Nonparametric Bayesian

A nonparametric mode is:

  1. A parametric model with #parameters that increases with the #data.
  2. A really large param model;
  3. A model over infinite dimensional function/measure spaces;
  4. A family of distributions that is dense in some large space.
Why nonparam models is better?
  1. “allows the data speak for itself”! board class of priors!
Victor’s Side note:
Nonparametric Bayesian’s advantage:
imagine you don’t know the number of modes in a distributions, e.g. K Gaussian distributions but K is unknown.
Using parametric way, you need to pin down one K as hypothesis then test it. Pick the optimal one K.
Well in nonparam, K can be a random variable, and the P(x | K) can be approximated by MLE/MAP.
Categories: research resources
  1. No comments yet.
  1. No trackbacks yet.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: