Sparse Multiscale Gaussian Process Regression

author: Christian Walder, Max Planck Institute for Biological Cybernetics, Max Planck Institute
published: July 29, 2008,   recorded: July 2008,   views: 5482
Categories

Slides

Related Open Educational Resources

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.
  Bibliography

Description

Most existing sparse Gaussian process (g.p.) models seek computational advantages by basing their computations on a set of m basis functions that are the covariance function of the g.p. with one of its two inputs fixed. We generalise this for the case of Gaussian covariance function, by basing our computations on m Gaussian basis functions with arbitrary diagonal covariance matrices (or length scales). For a fixed number of basis functions and any given criteria, this additional flexibility permits approximations no worse and typically better than was previously possible. We perform gradient based optimisation of the marginal likelihood, which costs O(m2n) time where n is the number of data points, and compare the method to various other sparse g.p. methods. Although we focus on g.p. regression, the central idea is applicable to all kernel based algorithms, and we also provide some results for the support vector machine (s.v.m.) and kernel ridge regression (k.r.r.). Our approach outperforms the other methods, particularly for the case of very few basis functions, i.e. a very high sparsity ratio.

See Also:

Download slides icon Download slides: icml08_walder_spg_01.pdf (556.4 KB)


Help icon Streaming Video Help

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Reviews and comments:

Comment1 Paul Goodhew, January 15, 2010 at 12:01 a.m.:

Christian, a very interesting paper.


Comment2 Jason Emery, May 7, 2011 at 12:38 p.m.:

Good to see you're using that massive fuckin brain dude. Well done.


Comment3 model-paper.com, May 13, 2023 at 11:19 a.m.:

While Modelpapers strives to provide better service in various ways and does not sell or give away your personal information other than what you want to make public, there are instances in which your mail may be model-paper.com exposed to the public. We are very aware of email spam and make every effort to protect every email.

Write your own review or comment:

make sure you have javascript enabled or clear this field: