Learning Coverage Functions and Private Release of Marginals

author: Pravesh Kothari, Department of Computer Science, University of Texas at Austin
published: July 15, 2014,   recorded: June 2014,   views: 2280


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 study the problem of approximating and learning coverage functions. A function c:2[n]→R+ is a coverage function, if there exists a universe U with non-negative weights w(u) for each u∈U and subsets A1,A2,…,An of U such that c(S)=∑u∈∪i∈SAiw(u). Alternatively, coverage functions can be described as non-negative linear combinations of monotone disjunctions. They are a natural subclass of submodular functions and arise in a number of applications.

We give an algorithm that for any γ,δ>0, given random and uniform examples of an unknown coverage function c, finds a function h that approximates c within factor 1+γ on all but δ-fraction of the points in time poly(n,1/γ,1/δ). This is the first fully-polynomial algorithm for learning an interesting class of functions in the demanding PMAC model of Balcan and Harvey (2011). Our algorithms are based on several new structural properties of coverage functions. Using the results in (Feldman and Kothari, 2014), we also show that coverage functions are learnable agnostically with excess ℓ1-error ϵ over all product and symmetric distributions in time nlog(1/ϵ). In contrast, we show that, without assumptions on the distribution, learning coverage functions is at least as hard as learning polynomial-size disjoint DNF formulas, a class of functions for which the best known algorithm runs in time 2O(n1/3) (Klivans and Servedio, 2004).

As an application of our learning results, we give simple differentially-private algorithms for releasing monotone conjunction counting queries with low average error. In particular, for any k≤n, we obtain private release of k-way marginals with average error α¯ in time nO(log(1/α¯)).

See Also:

Download slides icon Download slides: colt2014_kothari_learning.pdf (8.4 MB)

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: