中文
相关论文

相关论文: One Ring to Rule Them All: Certifiably Robust Geom…

200 篇论文

We initiate a systematic study of tolerant testers of image properties or, equivalently, algorithms that approximate the distance from a given image to the desired property (that is, the smallest fraction of pixels that need to change in…

数据结构与算法 · 计算机科学 2016-08-16 Piotr Berman , Meiram Murzabulatov , Sofya Raskhodnikova

Equivariant neural networks have proven to be effective for tasks with known underlying symmetries. However, optimizing equivariant networks can be tricky and best training practices are less established than for standard networks. In…

机器学习 · 计算机科学 2025-11-04 YuQing Xie , Tess Smidt

Outlier detection is an integral part of robust evaluation for crowdsourceable Quality of Experience (QoE) and has attracted much attention in recent years. In QoE for multimedia, outliers happen because of different test conditions, human…

多媒体 · 计算机科学 2014-10-23 Qianqian Xu , Ming Yan , Yuan Yao

Distributionally Robust (DR) optimization aims to certify worst-case risk within a Wasserstein uncertainty set. Current certifications typically rely either on global Lipschitz bounds, which are often conservative, or on local gradient…

最优化与控制 · 数学 2026-04-09 Hong T. M. Chu

In this paper, we study the \emph{sparse integer least squares problem} (SILS), an NP-hard variant of least squares with sparse $\{0, \pm 1\}$-vectors. We propose an $\ell_1$-based SDP relaxation, and a randomized algorithm for SILS, which…

最优化与控制 · 数学 2026-05-19 Alberto Del Pia , Dekun Zhou

The reduced-rank method exploits the distortion-variance tradeoff to yield superior solutions for classic problems in statistical signal processing such as parameter estimation and filtering. The central idea is to reduce the variance of…

信息论 · 计算机科学 2019-03-06 K. G. Nagananda , Pramod Khargonekar

Most existing distance metric learning methods assume perfect side information that is usually given in pairwise or triplet constraints. Instead, in many real-world applications, the constraints are derived from side information, such as…

机器学习 · 计算机科学 2012-03-19 Kaizhu Huang , Rong Jin , Zenglin Xu , Cheng-Lin Liu

We study the problem of exact support recovery based on noisy observations and present Refined Least Squares (RLS). Given a set of noisy measurement $$ \myvec{y} = \myvec{X}\myvec{\theta}^* + \myvec{\omega},$$ and $\myvec{X} \in…

统计理论 · 数学 2021-03-22 Ofir Lindenbaum , Stefan Steinerberger

Outliers widely occur in big-data applications and may severely affect statistical estimation and inference. In this paper, a framework of outlier-resistant estimation is introduced to robustify an arbitrarily given loss function. It has a…

统计方法学 · 统计学 2023-04-20 Yiyuan She , Zhifeng Wang , Jiahui Shen

The design of minimum-compliance bending-resistant structures with continuous cross-section parameters is a challenging task because of its inherent non-convexity. Our contribution develops a strategy that facilitates computing all…

最优化与控制 · 数学 2022-05-06 Marek Tyburec , Jan Zeman , Martin Kružík , Didier Henrion

Many nonconvex problems in robotics can be relaxed into convex formulations via Semi-Definite Programming (SDP) that can be solved to global optimality. The practical quality of these solutions, however, critically depends on rounding them…

机器人学 · 计算机科学 2025-10-02 Liangting Wu , Roberto Tron

Many geometric estimation problems take the form of synchronization over the special Euclidean group: estimate the values of a set of poses given noisy measurements of a subset of their pairwise relative transforms. This problem is…

机器人学 · 计算机科学 2017-02-13 David M. Rosen , Luca Carlone , Afonso S. Bandeira , John J. Leonard

The trust region subproblem (TRS) is to minimize a possibly nonconvex quadratic function over a Euclidean ball. There are typically two cases for (TRS), the so-called ``easy case'' and ``hard case''. Even in the ``easy case'', the sequence…

最优化与控制 · 数学 2022-07-13 Mengmeng Song , Yong Xia , Jinyang Zheng

We propose a novel method for computing exact pointwise robustness of deep neural networks for all convex $\ell_p$ norms. Our algorithm, GeoCert, finds the largest $\ell_p$ ball centered at an input point $x_0$, within which the output…

机器学习 · 计算机科学 2019-06-05 Matt Jordan , Justin Lewis , Alexandros G. Dimakis

The aim of this work is to certify lower bounds for real-valued multivariate functions, defined by semialgebraic or transcendental expressions. The certificate must be, eventually, formally provable in a proof system such as Coq. The…

符号计算 · 计算机科学 2014-04-18 Xavier Allamigeon , Stéphane Gaubert , Victor Magron , Benjamin Werner

Convex relaxations based on different hierarchies of linear/semi-definite programs have been used recently to devise approximation algorithms for various optimization problems. The approximation guarantee of these algorithms improves with…

数据结构与算法 · 计算机科学 2015-03-20 Venkatesan Guruswami , Ali Kemal Sinop

When computing bounds, spatial branch-and-bound algorithms often linearly outer approximate convex relaxations for non-convex expressions in order to capitalize on the efficiency and robustness of linear programming solvers. Considering…

Quadratic programs with box constraints involve minimizing a possibly nonconvex quadratic function subject to lower and upper bounds on each variable. This is a well-known NP-hard problem that frequently arises in various applications. We…

最优化与控制 · 数学 2023-03-14 Yuzhou Qiu , E. Alper Yıldırım

The analysis of a total least square problem (TLS) can be reduced to that of an associated core problem, which typically has lower dimension and improved solubility properties. Nevertheless, even a core problem may remain reducible,…

环与代数 · 数学 2026-05-12 Sijia Yu , Bruno Carpentieri , Yan-Fei Jing

In this paper, we study a fast approximation method for {\it large-scale high-dimensional} sparse least-squares regression problem by exploiting the Johnson-Lindenstrauss (JL) transforms, which embed a set of high-dimensional vectors into a…

统计理论 · 数学 2015-07-21 Tianbao Yang , Lijun Zhang , Qihang Lin , Rong Jin