Algorithms for Lipschitz Learning on Graphs

author: Sushant Sachdeva, Department of Computer Science, Yale University
published: Aug. 20, 2015,   recorded: July 2015,   views: 2927


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.


We develop fast algorithms for solving regression problems on graphs where one is given the value of a function at some vertices, and must find its smoothest possible extension to all vertices. The extension we compute is the absolutely minimal Lipschitz extension, and is the limit for large $p$ of $p$-Laplacian regularization. We present an algorithm that computes a minimal Lipschitz extension in expected linear time, and an algorithm that computes an absolutely minimal Lipschitz extension in expected time $O (m n)$. The latter algorithm has variants that seem to run much faster in practice. These extensions are particulary amenable to regularization: we can perform $l_{0}$ regularization on the given values in polynomial time and $l_{1}$ regularization on the graph edge weights in time $\widetilde{O} (m^{3/2})$. Our algorithms naturally extend to directed graphs.

See Also:

Download slides icon Download slides: colt2015_sachdeva_lipschitz_learning_01.pdf (1.6┬áMB)

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 Larry Heiser, March 22, 2021 at 7:51 a.m.:

Flame jets at the lower end heat all the materials in the kiln to high temperatures that range between 2,700 and 3,000 degrees Fahrenheit.
<a href="">Concrete Elite</a>

Comment2 Michael Keene, March 22, 2021 at 7:52 a.m.:

This high heat drives off, or calcines, the chemically combined water and carbon dioxide from the raw materials and forms new compounds.

Comment3 Karum, December 21, 2021 at 3:32 a.m.:

I really learned a lot. Thanks.

Write your own review or comment:

make sure you have javascript enabled or clear this field: