English
Related papers

Related papers: Robust Smoothed Analysis of a Condition Number for…

200 papers

The structured singular value $\mu_E$ for a linear subspace $E$ of $M_n(\mathbb C)$ is defined by \[ \mu_E(A)=1 / \inf\{\|X\| \ : \ X \in E, \ \det(I_n-AX)=0 \} \quad (A \in M_n(\mathbb{C})), \] and $\mu_E(A)=0$ if there is no $X \in E$…

Functional Analysis · Mathematics 2026-03-30 Sourav Pal , Nitin Tomar

We consider a square random matrix made by i.i.d. rows with any distribution and prove that, for any given dimension, the probability for the least singular value to be in [0; $\epsilon$) is at least of order $\epsilon$. This allows us to…

Probability · Mathematics 2020-04-16 Matteo Gregoratti , Davide Maran

Under some mild Markov assumptions it is shown that the problem of designing optimal sequential tests for two simple hypotheses can be formulated as a linear program. The result is derived by investigating the Lagrangian dual of the…

Statistics Theory · Mathematics 2015-02-24 Michael Fauss , Abdelhak M. Zoubir

We consider Continuous Linear Programs over a continuous finite time horizon $T$, with linear cost coefficient functions, linear right hand side functions, and a constant coefficient matrix, as well as their symmetric dual. We search for…

Optimization and Control · Mathematics 2014-12-02 Evgeny Shindin , Gideon Weiss

Given $X \subset R^n$, $\varepsilon \in (0,1)$, a parametrized family of probability distributions $(\mu\_{a})\_{a\in A}$ on $\Omega\subset R^p$, we consider the feasible set $X^*\_\varepsilon\subset X$ associated with the {\em…

Optimization and Control · Mathematics 2018-11-26 Jean Lasserre , Tillmann Weisser

Smoothed analysis of complexity bounds and condition numbers has been done, so far, on a case by case basis. In this paper we consider a reasonably large class of condition numbers for problems over the complex numbers and we obtain…

Numerical Analysis · Mathematics 2007-05-23 Peter Buergisser , Felipe Cucker , Martin Lotz

This paper presents a robust, distributed algorithm to solve general linear programs. The algorithm design builds on the characterization of the solutions of the linear program as saddle points of a modified Lagrangian function. We show…

Optimization and Control · Mathematics 2014-09-26 Dean Richert , Jorge Cortes

We consider the Cauchy problem for the defocusing cubic nonlinear Schr\"odinger equation in four space dimensions and establish almost sure local well-posedness and conditional almost sure scattering for random initial data in…

Analysis of PDEs · Mathematics 2019-02-07 Benjamin Dodson , Jonas Luhrmann , Dana Mendelson

The predictive quality of machine learning models is typically measured in terms of their (approximate) expected prediction accuracy or the so-called Area Under the Curve (AUC). Minimizing the reciprocals of these measures are the goals of…

Machine Learning · Statistics 2019-03-04 Hiva Ghanbari , Minhan Li , Katya Scheinberg

Randomized smoothing provides strong, model-agnostic robustness certificates, but existing guarantees are limited to single modalities, treating continuous and discrete inputs in isolation. This limitation becomes critical in multimodal…

Machine Learning · Computer Science 2026-05-14 Blaise Delattre , Hengyu Wu , Paul Caillon , Wei Yang Bryan Lim , Yang Cao

Randomized smoothing is the current state-of-the-art method for producing provably robust classifiers. While randomized smoothing typically yields robust $\ell_2$-ball certificates, recent research has generalized provable robustness to…

Machine Learning · Computer Science 2023-09-26 Samuel Pfrommer , Brendon G. Anderson , Somayeh Sojoudi

We consider the cubic nonlinear Schr\"odinger equation with a spatially rough potential, a key equation in the mathematical setup for nonlinear Anderson localization. Our study comprises two main parts: new optimal results on the…

Numerical Analysis · Mathematics 2024-03-26 Norbert J. Mauser , Yifei Wu , Xiaofei Zhao

We study randomized variants of two classical algorithms: coordinate descent for systems of linear equations and iterated projections for systems of linear inequalities. Expanding on a recent randomized iterated projection algorithm of…

Optimization and Control · Mathematics 2008-06-19 D. Leventhal , A. S. Lewis

Maintaining numerical stability in machine learning models is crucial for their reliability and performance. One approach to maintain stability of a network layer is to integrate the condition number of the weight matrix as a regularizing…

Machine Learning · Computer Science 2024-10-02 Rossen Nenov , Daniel Haider , Peter Balazs

In this note we establish existence and uniqueness of weak solutions of linear elliptic equation $\text{div}[\mathbf{A}(x) \nabla u] = \text{div}{\mathbf{F}(x)}$, where the matrix $\mathbf{A}$ is just measurable and its skew-symmetric part…

Analysis of PDEs · Mathematics 2018-04-17 Juraj Földes , Tuoc Phan

Given Boolean functions \( f, g : \mathbb{F}_2^n \to \{-1,+1\} \), we say they are {\em linearly isomorphic} if there exists \( A \in \mathrm{GL}_n(\mathbb{F}_2) \) such that \( f(x)=g(Ax) \) for all \( x \). We study this problem in the…

Computational Complexity · Computer Science 2026-01-14 Swarnalipa Datta , Arijit Ghosh , Chandrima Kayal , Manaswi Paraashar , Manmatha Roy

Random constraint satisfaction problems (CSPs) are known to exhibit threshold phenomena: given a uniformly random instance of a CSP with $n$ variables and $m$ clauses, there is a value of $m = \Omega(n)$ beyond which the CSP will be…

Data Structures and Algorithms · Computer Science 2016-11-07 Prasad Raghavendra , Satish Rao , Tselil Schramm

We prove that for a residual (and hence dense) subset $\mathcal{G}$ of Riemannian metrics on $S^{n+1}$ in the $C^{3}$ topology, no area-minimizing integral $n$-current that is a boundary admits a singular tangent cone which is linearly…

Differential Geometry · Mathematics 2026-04-17 Zehua Cheng

Linear regression is a fundamental and primitive problem in supervised machine learning, with applications ranging from epidemiology to finance. In this work, we propose methods for speeding up distributed linear regression. We do so by…

Information Theory · Computer Science 2024-04-02 Neophytos Charalambides , Hessam Mahdavifar , Mert Pilanci , Alfred O. Hero

Probabilistic smoothing is a standard tool for global optimization, but existing methods rely on Gaussian kernels and specific transforms, often resulting in strong hyperparameter sensitivity and limited robustness. We propose a general…

Machine Learning · Computer Science 2026-05-27 Kukyoung Jang , Taehyun Cho , Junrui Zhang , Ping Xu , Kyungjae Lee
‹ Prev 1 3 4 5 6 7 10 Next ›