More data speeds up training time in learning halfspaces over sparse vectors

author: Amit Daniely, Einstein Institute of Mathematics, The Hebrew University of Jerusalem
published: Nov. 7, 2014,   recorded: January 2014,   views: 1782


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.


The increased availability of data in recent years led several authors to ask whether it is possible to use data as a {\em computational} resource. That is, if more data is available, beyond the sample complexity limit, is it possible to use the extra examples to speed up the computation time required to perform the learning task? We give the first positive answer to this question for a {\em natural supervised learning problem} --- we consider agnostic PAC learning of halfspaces over 3-sparse vectors in {−1,1,0}n. This class is inefficiently learnable using O(n/ϵ2) examples. Our main contribution is a novel, non-cryptographic, methodology for establishing computational-statistical gaps, which allows us to show that, under a widely believed assumption that refuting random 3CNF formulas is hard, efficiently learning this class using O\left(n/\epsilon^2\right)examplesisimpossible.Wefurthershowthatunderstrongerhardnessassumptions,evenO\left(n^{1.499}/\epsilon^2\right)examplesdonotsuffice.Ontheotherhand,weshowanewalgorithmthatlearnsthisclassefficientlyusing\tilde{\Omega}\left(n^2/\epsilon^2\right)$ examples. This formally establishes the tradeoff between sample and computational complexity for a natural supervised learning problem.

See Also:

Download slides icon Download slides: machine_daniely_sparse_vectors_01.pdf (210.4 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 !

Write your own review or comment:

make sure you have javascript enabled or clear this field: