中文
相关论文

相关论文: Noise stability of functions with low influences: …

200 篇论文

In this paper we derive tight bounds on the expected value of products of {\em low influence} functions defined on correlated probability spaces. The proofs are based on extending Fourier theory to an arbitrary number of correlated…

概率论 · 数学 2009-06-01 Elchanan Mossel

We study the probability of Boolean functions with small max influence to become constant under random restrictions. Let $f$ be a Boolean function such that the variance of $f$ is $\Omega(1)$ and all its individual influences are bounded by…

计算复杂性 · 计算机科学 2022-08-19 Ronen Eldan , Avi Wigderson , Pei Wu

We show that all non-negative submodular functions have high {\em noise-stability}. As a consequence, we obtain a polynomial-time learning algorithm for this class with respect to any product distribution on $\{-1,1\}^n$ (for any constant…

机器学习 · 计算机科学 2011-06-14 Mahdi Cheraghchi , Adam Klivans , Pravesh Kothari , Homin K. Lee

We prove an invariance principle for functions on a slice of the Boolean cube, which is the set of all vectors {0,1}^n with Hamming weight k. Our invariance principle shows that a low-degree, low-influence function has similar distributions…

概率论 · 数学 2016-02-23 Yuval Filmus , Guy Kindler , Elchanan Mossel , Karl Wimmer

We extend, in the free probability framework, an invariance principle for multilinear homogeneous sums with low influences recently established in [E. Mossel, R. O'Donnell and K. Oleszkiewicz (2010). Noise stability of functions with low…

概率论 · 数学 2014-03-11 Aurélien Deya , Ivan Nourdin

We present a regularity lemma for Boolean functions $f:\{-1,1\}^n \to \{-1,1\}$ based on noisy influence, a measure of how locally correlated $f$ is with each input bit. We provide an application of the regularity lemma to weaken the…

计算复杂性 · 计算机科学 2016-10-25 Chris Jones

In a recent work with Kindler and Wimmer we proved an invariance principle for the slice for low-influence, low-degree functions. Here we provide an alternative proof for general low-degree functions, with no constraints on the influences.…

概率论 · 数学 2019-01-29 Yuval Filmus , Elchanan Mossel

Every Boolean function can be uniquely represented as a multilinear polynomial. The entropy and the total influence are two ways to measure the concentration of its Fourier coefficients, namely the monomial coefficients in this…

计算复杂性 · 计算机科学 2017-11-03 Rani Hod

We consider a variant of the classical notion of noise on the Boolean hypercube which gives rise to a new approach to inequalities regarding noise stability. We use this approach to give a new proof of the Majority is Stablest theorem by…

概率论 · 数学 2022-08-16 Ronen Eldan , Dan Mikulincer , Prasad Raghavendra

Gaussian bounds on noise correlation of functions play an important role in hardness of approximation, in quantitative social choice theory and in testing. The author (2008) obtained sharp gaussian bounds for the expected correlation of…

概率论 · 数学 2017-10-25 Elchanan Mossel

This paper discusses a general and useful stability principle which, roughly speaking, says that given a uniformly continuous function defined on an arbitrary metric space, if the function is bounded on the constraint set and we slightly…

最优化与控制 · 数学 2020-09-04 Daniel Reem , Simeon Reich , Alvaro De Pierro

The characteristic functional is the infinite-dimensional generalization of the Fourier transform for measures on function spaces. It characterizes the statistical law of the associated stochastic process in the same way as a characteristic…

概率论 · 数学 2014-01-29 Julien Fageot , Arash Amini , Michael Unser

The Majority is Stablest Theorem has numerous applications in hardness of approximation and social choice theory. We give a new proof of the Majority is Stablest Theorem by induction on the dimension of the discrete cube. Unlike the…

计算复杂性 · 计算机科学 2012-11-07 Anindya De , Elchanan Mossel , Joe Neeman

We study causal inference in a multi-environment setting, in which the functional relations for producing the variables from their direct causes remain the same across environments, while the distribution of exogenous noises may vary. We…

机器学习 · 计算机科学 2017-05-29 AmirEmad Ghassami , Saber Salehkaleybar , Negar Kiyavash , Kun Zhang

Study samples often differ from the target populations of inference and policy decisions in non-random ways. Researchers typically believe that such departures from random sampling -- due to changes in the population over time and space, or…

统计方法学 · 统计学 2023-07-20 Tamara Broderick , Ryan Giordano , Rachael Meager

A notable result from analysis of Boolean functions is the Basic Invariance Principle (BIP), a quantitative nonlinear generalization of the Central Limit Theorem for multilinear polynomials. We present a generalization of the BIP for…

信息论 · 计算机科学 2022-08-18 Alexander Mariona , Homa Esfahanizadeh , Rafael G. L. D'Oliveira , Muriel Médard

The stability of Boolean networks has attracted much attention due to its wide applications in describing the dynamics of biological systems. During the past decades, much effort has been invested in unveiling how network structure and…

物理与社会 · 物理学 2018-03-21 Jiannan Wang , Sen Pei , Wei Wei , Xiangnan Feng , Zhiming Zheng

Stochastic inverse problems considered in this article consist of estimating the probability distributions of intrinsically random inputs of computer models. These estimations are based on observable outputs affected by model noise, and…

统计理论 · 数学 2025-03-17 Nicolas Bousquet , Mélanie Blazère , Thomas Cerbelaud

Questions of noise stability play an important role in hardness of approximation in computer science as well as in the theory of voting. In many applications, the goal is to find an optimizer of noise stability among all possible partitions…

概率论 · 数学 2017-02-17 Anindya De , Elchanan Mossel , Joe Neeman

This paper studies least-square regression penalized with partly smooth convex regularizers. This class of functions is very large and versatile allowing to promote solutions conforming to some notion of low-complexity. Indeed, they force…

最优化与控制 · 数学 2014-07-01 Samuel Vaiter , Gabriel Peyré , Jalal M. Fadili
‹ 上一页 1 2 3 10 下一页 ›