English
Related papers

Related papers: A Duality Between Depth-Three Formulas and Approxi…

200 papers

We present a general technique for the analysis of first-order methods. The technique relies on the construction of a duality gap for an appropriate approximation of the objective function, where the function approximation improves as the…

Optimization and Control · Mathematics 2019-12-12 Jelena Diakonikolas , Lorenzo Orecchia

We prove comparison principles for nonlinear potential theories in euclidian spaces in a very straightforward manner from duality and monotonicity. We shall also show how to deduce comparison principles for nonlinear differential operators,…

Analysis of PDEs · Mathematics 2020-09-04 Marco Cirant , F. Reese Harvey , H. Blaine Lawson, , Kevin R. Payne

We consider a problem of approximating the size of the largest clique in a graph, with a monotone circuit. Concretely, we focus on distinguishing a random Erd\H{o}s-Renyi graph $\mathcal{G}_{n,p}$, with $p=n^{-\frac{2}{\alpha-1}}$ chosen…

Computational Complexity · Computer Science 2025-01-17 Jarosław Błasiok , Linus Meierhöfer

We prove an exponential size separation between depth 2 and depth 3 neural networks (with real inputs), when approximating a $\mathcal{O}(1)$-Lipschitz target function to constant accuracy, with respect to a distribution with support in the…

Machine Learning · Computer Science 2024-11-08 Itay Safran , Daniel Reichman , Paul Valiant

We design an efficient data structure for computing a suitably defined approximate depth of any query point in the arrangement $\mathcal{A}(S)$ of a collection $S$ of $n$ halfplanes or triangles in the plane or of halfspaces or simplices in…

Computational Geometry · Computer Science 2020-06-23 Dror Aiger , Haim Kaplan , Micha Sharir

We discuss the computational complexity of approximating maximum a posteriori inference in sum-product networks. We first show NP-hardness in trees of height two by a reduction from maximum independent set; this implies non-approximability…

Artificial Intelligence · Computer Science 2017-09-06 Diarmaid Conaty , Denis D. Mauá , Cassio P. de Campos

The degrees of polynomials representing or approximating Boolean functions are a prominent tool in various branches of complexity theory. Sherstov recently characterized the minimal degree deg_{\eps}(f) among all polynomials (over the…

Quantum Physics · Physics 2008-02-15 Ronald de Wolf

We study the size blow-up that is necessary to convert an algebraic circuit of product-depth $\Delta+1$ to one of product-depth $\Delta$ in the multilinear setting. We show that for every positive $\Delta = \Delta(n) = o(\log n/\log \log…

Computational Complexity · Computer Science 2018-04-10 Suryajith Chillara , Christian Engels , Nutan Limaye , Srikanth Srinivasan

Let $\Poly$ be a simple polygon with $n$ vertices. The \emph{dual graph} $\triang^*$ of a triangulation~$\triang$ of~$\Poly$ is the graph whose vertices correspond to the bounded faces of $\triang$ and whose edges connect those faces…

Computational Geometry · Computer Science 2017-10-31 Matias Korman , Stefan Langerman , Wolfgang Mulzer , Alexander Pilz , Maria Saumell , Birgit Vogtenhuber

Agrawal and Vinay [AV08] showed how any polynomial size arithmetic circuit can be thought of as a depth four arithmetic circuit of subexponential size. The resulting circuit size in this simulation was more carefully analyzed by Korian…

Computational Complexity · Computer Science 2017-08-02 Suryajith Chillara , Mrinal Kumar , Ramprasad Saptharishi , V Vinay

Approximating a convex function by a polyhedral function that has a limited number of facets is a fundamental problem with applications in various fields, from mitigating the curse of dimensionality in optimal control to bi-level…

Optimization and Control · Mathematics 2025-09-05 Abdellah Bulaich Mehamdi , Wim van Ackooij , Luce Brotcorne , Stéphane Gaubert , Quentin Jacquet

We formally extend the CFT techniques introduced in arXiv:1505.00963, to $\phi^{\frac{2d_0}{d_0-2}}$ theory in $d=d_0-\epsilon$ dimensions and use it to compute anomalous dimensions near $d_0=3, 4$ in a unified manner. We also do a similar…

High Energy Physics - Theory · Physics 2015-10-23 Pallab Basu , Chethan Krishnan

In large-data applications, it is desirable to design algorithms with a high degree of parallelization. In the context of submodular optimization, adaptive complexity has become a widely-used measure of an algorithm's "sequentiality".…

Data Structures and Algorithms · Computer Science 2020-04-22 Wenzheng Li , Paul Liu , Jan Vondrak

This paper quantitatively characterizes the approximation power of deep feed-forward neural networks (FNNs) in terms of the number of neurons. It is shown by construction that ReLU FNNs with width $\mathcal{O}\big(\max\{d\lfloor…

Numerical Analysis · Mathematics 2021-01-15 Zuowei Shen , Haizhao Yang , Shijun Zhang

A major open problem in proof complexity is to demonstrate that random 3-CNFs with a linear number of clauses require super-polynomial size refutations in bounded-depth Frege systems. We take the first step towards addressing this question…

Computational Complexity · Computer Science 2024-09-04 Svyatoslav Gryaznov , Navid Talebanfard

Given a monotonically decreasing $\psi: \mathbb{N} \to [0,\infty)$, Khintchine's Theorem provides an efficient tool to decide whether, for almost every $\alpha \in \mathbb{R}$, there are infinitely many $(p,q) \in \mathbb{Z}^2$ such that…

Number Theory · Mathematics 2024-03-19 Lorenz Frühwirth , Manuel Hauke

An important tool to quantify the likeness of two probability measures are f-divergences, which have seen widespread application in statistics and information theory. An example is the total variation, which plays an exceptional role among…

Probability · Mathematics 2009-03-11 Jochen Bröcker

The aim of this expository article is to present recent developments in the centuries old discussion on the interrelations between continuous and differentiable real valued functions of one real variable. The truly new results include,…

Functional Analysis · Mathematics 2018-06-29 Krzysztof C. Ciesielski , Juan B. Seoane Sepúlveda

A theorem of Hoischen states that given a positive continuous function $\varepsilon:\mathbb{R}\to\mathbb{R}$, an integer $n\geq 0$, and a closed discrete set $E\subseteq\mathbb{R}$, any $C^n$ function $f:\mathbb{R}\to\mathbb{R}$ can be…

Classical Analysis and ODEs · Mathematics 2026-01-01 Maxim R. Burke

A {\it two-dimensional continued fraction expansion} is a map $\mu$ assigning to every $x \in\mathbb R^2\setminus\mathbb Q^2$ a sequence $\mu(x)=T_0,T_1,\dots$ of triangles $T_n$ with vertices $x_{ni}=(p_{ni}/d_{ni},q_{ni}/d_{ni})\in\mathbb…

Number Theory · Mathematics 2017-05-10 Daniele Mundici