Ryan O'Donnell

Learning intersections and thresholds of halfspaces

We give the first polynomial time algorithm to learn any function of a constant number of halfspaces under the uniform distribution to within any constant error parameter. We also give the first quasipolynomial time algorithm for learning any function of a polylog number of polynomial-weight halfspaces under any distribution. As special cases of these results we obtain algorithms for learning intersections and thresholds of halfspaces. Our uniform distribution learning algorithms involve a novel non-geometric approach to learning halfspaces; we use Fourier techniques together with a careful analysis of the noise sensitivity of functions of halfspaces. Our algorithms for learning under any distribution use techniques from real approximation theory to construct low degree polynomial threshold functions.

Optimal inapproximability results for MAX-CUT and other 2-variable CSPs?

In this paper, we give evidence suggesting that MAX-CUT is NP-hard to approximate to within a factor of /spl alpha//sub cw/+ /spl epsi/, for all /spl epsi/ > 0, where /spl alpha//sub cw/ denotes the approximation ratio achieved by the Goemans-Williamson algorithm (1995). /spl alpha//sub cw/ /spl ap/ .878567. This result is conditional, relying on two conjectures: a) the unique games conjecture of Khot; and, b) a very believable conjecture we call the majority is stablest conjecture. These results indicate that the geometric nature of the Goemans-Williamson algorithm might be intrinsic to the MAX-CUT problem. The same two conjectures also imply that it is NP-hard to (/spl beta/ + /spl epsi/)-approximate MAX-2SAT, where /spl beta/ /spl ap/ .943943 is the minimum of (2 + (2//spl pi/) /spl theta/)/(3 - cos(/spl theta/)) on (/spl pi//2, /spl pi/). Motivated by our proof techniques, we show that if the MAX-2CSP and MAX-2SAT problems are slightly restricted - in a way that seems to retain all their hardness -then they have (/spl alpha//sub GW/-/spl epsi/)- and (/spl beta/ - /spl epsi/)-approximation algorithms, respectively. Though we are unable to prove the majority is stablest conjecture, we give some partial results and indicate possible directions of attack. Our partial results are enough to imply that MAX-CUT is hard to (3/4 + 1/(2/spl pi/) + /spl epsi/)-approximate (/spl ap/ .909155), assuming only the unique games conjecture. We also discuss MAX-2CSP problems over non-Boolean domains and state some related results and conjectures. We show, for example, that the unique games conjecture implies that it is hard to approximate MAX-2LIN(q) to within any constant factor.

Some topics in analysis of boolean functions

This article accompanies a tutorial talk given at the 40th ACM STOC conference. In it, we give a brief introduction to Fourier analysis of boolean functions and then discuss some applications: Arrows Theorem and other ideas from the theory of Social Choice; the Bonami-Beckner Inequality as an extension of Chernoff/Hoeffding bounds to higher-degree polynomials; and, hardness for approximation algorithms.

Hardness amplification within NP

(MATH) In this paper we investigate the following question: If

Learning functions of k relevant variables

\np

Learning juntas

is slightly hard on average, is it very hard on average? We show the answer is yes; if there is a function in

New degree bounds for polynomial threshold functions

\np

On the noise sensitivity of monotone functions

which is \mbox{

Testing Fourier Dimensionality and Sparsity

(1-1/\poly(n))

Non-interactive correlation distillation, inhomogeneous Markov chains, and the reverse Bonami-Beckner inequality

}-hard for circuits of polynomial size, then there is a function in