中文
相关论文

相关论文: Tackling heavy-tailed noise in distributed estimat…

200 篇论文

We consider distributed recursive estimation of consensus+innovations type in the presence of heavy-tailed sensing and communication noises. We allow that the sensing and communication noises are mutually correlated while independent…

最优化与控制 · 数学 2023-11-13 Manojlo Vukovic , Dusan Jakovetic , Dragana Bajovic , Soummya Kar

This paper studies the distributed optimization problem under the influence of heavy-tailed gradient noises. Here, a heavy-tailed noise means that the noise does not necessarily satisfy the bounded variance assumption. Instead, it satisfies…

最优化与控制 · 数学 2025-05-12 Chao Sun , Huiming Zhang , Bo Chen , Li Yu

We consider a standard distributed optimization problem in which networked nodes collaboratively minimize the sum of their locally known convex costs. For this setting, we address for the first time the fundamental problem of design and…

最优化与控制 · 数学 2025-06-02 Manojlo Vukovic , Dusan Jakovetic , Dragana Bajovic , Soummya Kar

In existing distributed stochastic optimization studies, it is usually assumed that the gradient noise has a bounded variance. However, recent research shows that the heavy-tailed noise, which allows an unbounded variance, is closer to…

最优化与控制 · 数学 2025-05-15 Jun Hu , Chao Sun , Bo Chen , Jianzheng Wang , Zheming Wang

We address a parametric joint detection-estimation problem for discrete signals of the form $x(t) = \sum_{n=1}^{N} \alpha_n e^{-i \lambda_n t } + \epsilon_t$, $t \in \mathbb{N}$, with an additive noise represented by independent centered…

经典分析与常微分方程 · 数学 2018-08-14 Illya M. Karabash , Jürgen Prestin

This paper studies distributed estimation and support recovery for high-dimensional linear regression model with heavy-tailed noise. To deal with heavy-tailed noise whose variance can be infinite, we adopt the quantile regression loss…

统计方法学 · 统计学 2020-09-21 Xi Chen , Weidong Liu , Xiaojun Mao , Zhuoyi Yang

We study high-dimensional signal recovery from non-linear measurements with design vectors having elliptically symmetric distribution. Special attention is devoted to the situation when the unknown signal belongs to a set of low statistical…

统计理论 · 数学 2016-11-14 Larry Goldstein , Stanislav Minsker , Xiaohan Wei

In this paper, we address the problem of simultaneous classification and estimation of hidden parameters in a sensor network with communications constraints. In particular, we consider a network of noisy sensors which measure a common…

多智能体系统 · 计算机科学 2012-06-19 Fabio Fagnani , Sophie M. Fosson , Chiara Ravazzi

Heavy-tailed stochastic gradient noise, commonly observed in transformer models, can destabilize the optimization process. Recent works mainly focus on developing and understanding approaches to address heavy-tailed noise in the centralized…

机器学习 · 计算机科学 2026-02-23 Junfei Sun , Dixi Yao , Xuchen Gong , Tahseen Rabbani , Manzil Zaheer , Tian Li

In this paper, the problem of distributed optimization is studied via a network of agents. Each agent only has access to a noisy gradient of its own objective function, and can communicate with its neighbors via a network. To handle this…

最优化与控制 · 数学 2025-06-19 Yuchen Yang , Kaihong Lu , Long Wang

A distributed average consensus algorithm robust to a wide range of impulsive channel noise distributions is proposed. This work is the first of its kind in the literature to propose a consensus algorithm which relaxes the requirement of…

系统与控制 · 计算机科学 2015-06-22 Sivaraman Dasarathan , Cihan Tepedelenlioglu , Mahesh Banavar , Andreas Spanias

We study the distributed stochastic optimization (DSO) problem under a heavy-tailed noise condition by utilizing a multi-agent system. Despite the extensive research on DSO algorithms used to solve DSO problems under light-tailed noise…

最优化与控制 · 数学 2025-09-23 Zhan Yu , Lan Liao , Deming Yuan , Daniel W. C. Ho , Ding-Xuan Zhou

Recent works have proposed incorporating heavy-tailed (HT) noise into diffusion- and flow-based generative models, with the goals of better recovering the tails of target distributions and improving generative diversity. This motivation is…

机器学习 · 计算机科学 2026-05-14 Hamza Cherkaoui , Hélène Halconruy , Antonio Ocello

The paper studies distributed static parameter (vector) estimation in sensor networks with nonlinear observation models and noisy inter-sensor communication. It introduces \emph{separably estimable} observation models that generalize the…

多智能体系统 · 计算机科学 2012-05-21 Soummya Kar , Jose M. F. Moura , Kavita Ramanan

Most existing methods that cope with noisy labels usually assume that the class distributions are well balanced, which has insufficient capacity to deal with the practical scenarios where training samples have imbalanced distributions. To…

计算机视觉与模式识别 · 计算机科学 2022-09-27 Chaowei Fang , Lechao Cheng , Huiyan Qi , Dingwen Zhang

We propose a novel iterative algorithm for estimating a deterministic but unknown parameter vector in the presence of model uncertainties. This iterative algorithm is based on a system model where an overall noise term describes both, the…

统计理论 · 数学 2017-11-27 Oliver Lang , Michael Lunglmayr , Mario Huemer

Distributed optimization has become the default training paradigm in modern machine learning due to the growing scale of models and datasets. To mitigate communication overhead, local updates are often applied before global aggregation,…

机器学习 · 计算机科学 2025-08-15 Su Hyeong Lee , Manzil Zaheer , Tian Li

Score-based model research in the last few years has produced state of the art generative models by employing Gaussian denoising score-matching (DSM). However, the Gaussian noise assumption has several high-dimensional limitations,…

机器学习 · 计算机科学 2022-04-13 Jacob Deasy , Nikola Simidjievski , Pietro Liò

A new estimator is proposed for estimating the tail exponent of a heavy-tailed distribution. This estimator, referred to as the layered Hill estimator, is a generalization of the traditional Hill estimator, building upon a layered structure…

统计理论 · 数学 2026-04-20 Taegyu Kang , Takashi Owada

This paper proposes a distributed algorithm for average consensus in a multi-agent system under a fixed bidirectional communication topology, in the presence of malicious agents (nodes) that may try to influence the average consensus…

多智能体系统 · 计算机科学 2023-09-06 Christoforos N. Hadjicostis , Alejandro D. Dominguez-Garcia
‹ 上一页 1 2 3 10 下一页 ›