Noise Stable Halfspaces are Close to Very Small Juntas
نویسندگان
چکیده
Bourgain [Bou02] showed that any noise stable Boolean function f can be well-approximated by a junta. In this note we give an exponential sharpening of the parameters of Bourgain’s result under the additional assumption that f is a halfspace.
منابع مشابه
Noise-Resistant Boolean-Functions are Juntas
We consider Boolean functions over n binary variables, and a general p-biased, product measure over the inputs. We show that if f is of low-degree, that is, so that the weight of f on the Fourier-Walsh products of size larger than k is small, then f is close to a junta, namely, a function which depends only on very small, related to k however unrelated to n, number of variables. We conclude tha...
متن کاملTesting halfspaces
This paper addresses the problem of testing whether a Boolean-valued function f is a halfspace, i.e. a function of the form f(x) = sgn(w ·x−θ).We consider halfspaces over the continuous domain R (endowed with the standard multivariate Gaussian distribution) as well as halfspaces over the Boolean cube {−1, 1} (endowed with the uniform distribution). In both cases we give an algorithm that distin...
متن کاملLow degree almost Boolean functions are sparse juntas
Nisan and Szegedy showed that low degree Boolean functions are juntas. Kindler and Safra showed that low degree functions which are almost Boolean are close to juntas. Their result holds with respect to μp for every constant p. When p is allowed to be very small, new phenomena emerge. For example, the function y1 + · · · + yε/p (where yi ∈ {0, 1}) is close to Boolean but not close to a junta. W...
متن کامل2 Learning Monotone Boolean Functions
Last time we finished the discussion about KM algorithm and its application. We also covered sparse Fourier representations and k-juntas of parities. In the end we started to talk about learning monotone Boolean functions and influence of such functions. Today We will first finish discussion about learning monotone Boolean functions. Then we will also talk about learning k-juntas of halfspaces....
متن کاملLearning Juntas in the Presence of Noise
We investigate the combination of two major challenges in computational learning: dealing with huge amounts of irrelevant information and learning from noisy data. It is shown that large classes of Boolean concepts that depend only on a small fraction of their variables—so-called juntas—can be learned efficiently from uniformly distributed examples that are corrupted by random attribute and cla...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Chicago J. Theor. Comput. Sci.
دوره 2016 شماره
صفحات -
تاریخ انتشار 2016