English
Related papers

Related papers: Tight Bounds on $\ell_1$ Approximation and Learnin…

200 papers

We study monotonicity testing of functions $f \colon \{0,1\}^d \to \{0,1\}$ using sample-based algorithms, which are only allowed to observe the value of $f$ on points drawn independently from the uniform distribution. A classic result by…

Data Structures and Algorithms · Computer Science 2024-08-21 Hadley Black

The approximate degree of a Boolean function is the least degree of a real multilinear polynomial approximating it in the $\ell_\infty$-norm over the Boolean hypercube. We show that the approximate degree of the Bipartite Perfect Matching…

Discrete Mathematics · Computer Science 2022-03-03 Gal Beniamini

We study the problem of learning nonparametric distributions in a finite mixture, and establish tight bounds on the sample complexity for learning the component distributions in such models. Namely, we are given i.i.d. samples from a pdf…

Machine Learning · Computer Science 2023-07-06 Bryon Aragam , Wai Ming Tai

We show that if $A \subset [k]^n$, then $A$ is $\epsilon$-close to a junta depending upon at most $\exp(O(|\partial A|/(k^{n-1}\epsilon)))$ coordinates, where $\partial A$ denotes the edge-boundary of $A$ in the $\ell^1$-grid. This is sharp…

Combinatorics · Mathematics 2015-08-18 Itai Benjamini , David Ellis , Ehud Friedgut , Nathan Keller , Arnab Sen

Submodular function minimization is well studied, and existing algorithms solve it exactly or up to arbitrary accuracy. However, in many applications, such as structured sparse learning or batch Bayesian optimization, the objective function…

Machine Learning · Computer Science 2022-03-10 Marwa El Halabi , Stefanie Jegelka

We characterize the model spaces $K_\Theta$ in which functions with smooth boundary extensions are dense. It is shown that such approximations are possible if and only if the singular measure associated to the singular inner factor of…

Functional Analysis · Mathematics 2021-06-18 Adem Limani , Bartosz Malman

Popular iterative algorithms such as boosting methods and coordinate descent on linear models converge to the maximum $\ell_1$-margin classifier, a.k.a. sparse hard-margin SVM, in high dimensional regimes where the data is linearly…

Machine Learning · Statistics 2023-01-23 Stefan Stojanovic , Konstantin Donhauser , Fanny Yang

The approximate degree of a Boolean function $f: \{-1, 1\}^n \to \{-1, 1\}$ is the minimum degree of a real polynomial that approximates $f$ to within error $1/3$ in the $\ell_\infty$ norm. In an influential result, Aaronson and Shi (J. ACM…

Computational Complexity · Computer Science 2015-03-27 Mark Bun , Justin Thaler

We prove a lower bound of $\tilde{\Omega}(n^{1/3})$ for the query complexity of any two-sided and adaptive algorithm that tests whether an unknown Boolean function $f:\{0,1\}^n\rightarrow \{0,1\}$ is monotone or far from monotone. This…

Computational Complexity · Computer Science 2017-08-22 Xi Chen , Erik Waingarten , Jinyu Xie

The manifold hypothesis says that natural high-dimensional data lie on or around a low-dimensional manifold. The recent success of statistical and learning-based methods in very high dimensions empirically supports this hypothesis,…

Machine Learning · Computer Science 2025-05-06 Hong Ye Tan , Subhadip Mukherjee , Junqi Tang , Carola-Bibiane Schönlieb

The sensitivity of a Boolean function f is the maximum over all inputs x, of the number of sensitive coordinates of x. The well-known sensitivity conjecture of Nisan (see also Nisan and Szegedy) states that every sensitivity-s Boolean…

Computational Complexity · Computer Science 2016-04-27 Parikshit Gopalan , Rocco Servedio , Avishay Tal , Avi Wigderson

Single hidden layer feedforward neural networks can represent multivariate functions that are sums of ridge functions. These ridge functions are defined via an activation function and customizable weights. The paper deals with best…

Functional Analysis · Mathematics 2020-11-24 Steffen Goebbels

A set function is called XOS if it can be represented by the maximum of additive functions. When such a representation is fixed, the number of additive functions required to define the XOS function is called the width. In this paper, we…

Data Structures and Algorithms · Computer Science 2020-07-09 Yuval Filmus , Yasushi Kawase , Yusuke Kobayashi , Yutaro Yamaguchi

A key challenge in scientific machine learning is solving partial differential equations (PDEs) on complex domains, where the curved geometry complicates the approximation of functions and their derivatives required by differential…

Numerical Analysis · Mathematics 2025-09-26 Hanfei Zhou , Lei Shi

In this paper, we further extend the study of function-correcting codes in the homogeneous metric over a chain ring $\mathbb{Z}_{2^s}$ for broader classes of functions, namely, locally bounded functions and linear functions, and for weight…

Information Theory · Computer Science 2026-03-17 Gyanendra K. Verma , Abhay Kumar Singh

Submodular maximization under various constraints is a fundamental problem studied continuously, in both computer science and operations research, since the late $1970$'s. A central technique in this field is to approximately optimize the…

Data Structures and Algorithms · Computer Science 2023-11-03 Niv Buchbinder , Moran Feldman

An apparently ideal way to generate continuous bounded stochastic processes is to consider the stochastically perturbed motion of a point of small mass in an infinite potential well, under overdamped approximation. Here, however, we show…

Mathematical Physics · Physics 2017-09-26 Dario Domingo , Alberto d Onofrio , Franco Flandoli

Let us assume that $f$ is a continuous function defined on the unit ball of $\mathbb R^d$, of the form $f(x) = g (A x)$, where $A$ is a $k \times d$ matrix and $g$ is a function of $k$ variables for $k \ll d$. We are given a budget $m \in…

Numerical Analysis · Mathematics 2012-01-18 Massimo Fornasier , Karin Schnass , Jan Vybiral

For smooth bounded domains in $\mathbb{R}$, we prove upper and lower $L^2$ bounds on the boundary data of Neumann eigenfunctions, and prove quasi-orthogonality of this boundary data in a spectral window. The bounds are tight in the sense…

Analysis of PDEs · Mathematics 2018-11-14 Alex Barnett , Andrew Hassell , Melissa Tacy

We study the computational power of polynomial threshold functions, that is, threshold functions of real polynomials over the boolean cube. We provide two new results bounding the computational power of this model. Our first result shows…

Computational Complexity · Computer Science 2009-11-29 Ido Ben-Eliezer , Shachar Lovett , Ariel Yadin