Average Sensitivity and Noise Sensitivity of Polynomial Threshold Functions

We give the first nontrivial upper bounds on the Boolean average sensitivity and noise sensitivity of degree-$d$ polynomial threshold functions (PTFs). Our bound on the Boolean average sensitivity of PTFs represents the first progress toward the resolution of a conjecture of Gotsman and Linial [Combinatorica, 14 (1994), pp. 35--50], which states that the symmetric function slicing the middle $d$ layers of the Boolean hypercube has the highest average sensitivity of all degree-$d$ PTFs. Via the $L_1$ polynomial regression algorithm of Kalai et al. [SIAM J. Comput., 37 (2008), pp. 1777--1805], our bound on Boolean noise sensitivity yields the first polynomial-time agnostic learning algorithm for the broad class of constant-degree PTFs under the uniform distribution. To obtain our bound on the Boolean average sensitivity of PTFs, we generalize the “critical-index” machinery of [R. Servedio, Comput. Complexity, 16 (2007), pp. 180--209] (which in that work applies to halfspaces, i.e., degree-1 PTFs) to general...

[1]  Ryan O'Donnell,et al.  Learning Monotone Decision Trees in Polynomial Time , 2007, SIAM J. Comput..

[2]  Ryan O'Donnell,et al.  Polynomial regression under arbitrary product distributions , 2010, Machine Learning.

[3]  William Feller,et al.  An Introduction to Probability Theory and Its Applications , 1967 .

[4]  Y. Peres.  Noise Stability of Weighted Majority , 2004, math/0412377.

[5]  Rocco A. Servedio,et al.  Bounded Independence Fools Halfspaces , 2009, 2009 50th Annual IEEE Symposium on Foundations of Computer Science.

[6]  Rocco A. Servedio,et al.  Learnability beyond AC0 , 2002, STOC '02.

[7]  Rocco A. Servedio,et al.  Improved Approximation of Linear Threshold Functions , 2009, 2009 24th Annual IEEE Conference on Computational Complexity.

[8]  Ryan O'Donnell,et al.  On the Fourier tails of bounded functions over the discrete cube , 2006, STOC '06.

[9]  Ryan O'Donnell,et al.  Learning monotone decision trees in polynomial time , 2006, 21st Annual IEEE Conference on Computational Complexity (CCC'06).

[10]  Ryan O'Donnell,et al.  Noise stability of functions with low influences: Invariance and optimality , 2005, 46th Annual IEEE Symposium on Foundations of Computer Science (FOCS'05).

[11]  Yaoyun Shi.  Lower bounds of quantum black-box complexity and degree of approximating polynomials by influence of Boolean variables , 2000, Inf. Process. Lett..

[12]  Ryan O'Donnell,et al.  Every decision tree has an influential variable , 2005, 46th Annual IEEE Symposium on Foundations of Computer Science (FOCS'05).

[13]  Elchanan Mossel,et al.  On the noise sensitivity of monotone functions , 2003, Random Struct. Algorithms.

[14]  I. Benjamini,et al.  Noise sensitivity of Boolean functions and applications to percolation , 1998 .

[15]  Shai Shalev-Shwartz,et al.  Agnostically Learning Halfspaces with Margin Errors , 2009 .

[16]  Nathan Linial,et al.  The influence of variables on Boolean functions , 1988, [Proceedings 1988] 29th Annual Symposium on Foundations of Computer Science.

[17]  Adam Tauman Kalai,et al.  Agnostically learning decision trees , 2008, STOC.

[18]  J. Bourgain,et al.  Influences of Variables and Threshold Intervals under Group Symmetries , 1997 .

[19]  Daniel M. Kane.  The Gaussian Surface Area and Noise Sensitivity of Degree-d Polynomial Threshold Functions , 2010, 2010 IEEE 25th Annual Conference on Computational Complexity.

[20]  Noam Nisan,et al.  Constant depth circuits, Fourier transform, and learnability , 1989, 30th Annual Symposium on Foundations of Computer Science.

[21]  Ryan O'Donnell,et al.  Learning Geometric Concepts via Gaussian Surface Area , 2008, 2008 49th Annual IEEE Symposium on Foundations of Computer Science.

[22]  Nathan Linial,et al.  Spectral properties of threshold functions , 1994, Comb..

[23]  W. Beckner.  Inequalities in Fourier analysis , 1975 .

[24]  A. Carbery,et al.  Distributional and L-q norm inequalities for polynomials over convex bodies in R-n , 2001 .

[25]  Rocco A. Servedio,et al.  A Regularity Lemma and Low-Weight Approximators for Low-Degree Polynomial Threshold Functions , 2014, Theory Comput..

[26]  Rocco A. Servedio,et al.  Every Linear Threshold Function has a Low-Weight Approximator , 2006, 21st Annual IEEE Conference on Computational Complexity (CCC'06).

[27]  O. Schramm,et al.  Quantitative noise sensitivity and exceptional times for percolation , 2005, math/0504586.

[28]  Feller William,et al.  An Introduction To Probability Theory And Its Applications , 1950 .

[29]  Rocco A. Servedio,et al.  Learning intersections and thresholds of halfspaces , 2002, The 43rd Annual IEEE Symposium on Foundations of Computer Science, 2002. Proceedings..

[30]  I. Benjamini,et al.  Noise sensitivity of Boolean functions and applications to percolation , 1998, math/9811157.

[31]  Johan Håstad,et al.  Randomly supported independence and resistance , 2009, STOC '09.

[32]  Nader H. Bshouty,et al.  On the Fourier spectrum of monotone functions , 1996, JACM.

[33]  Ehud Friedgut,et al.  Boolean Functions With Low Average Sensitivity Depend On Few Coordinates , 1998, Comb..

[34]  Adam Tauman Kalai,et al.  On agnostic boosting and parity learning , 2008, STOC.

[35]  Rocco A. Servedio,et al.  Agnostically learning halfspaces , 2005, 46th Annual IEEE Symposium on Foundations of Computer Science (FOCS'05).

[36]  Prahladh Harsha,et al.  Bounding the Sensitivity of Polynomial Threshold Functions , 2014, Theory Comput..

[37]  J. Bell.  Gaussian Hilbert spaces , 2015 .

[38]  Rocco A. Servedio,et al.  Learning and Lower Bounds for AC0 with Threshold Gates , 2010, APPROX-RANDOM.

[39]  Prasad Raghavendra,et al.  Average Sensitivity and Noise Sensitivity of Polynomial Threshold Functions , 2009, SIAM J. Comput..

[40]  Ryan O'Donnell,et al.  The chow parameters problem , 2008, SIAM J. Comput..