English
Related papers

Related papers: New Solutions Based on the Generalized Eigenvalue …

200 papers

Submodular function maximization is a critical building block for diverse tasks, such as document summarization, sensor placement, and image segmentation. Yet its practical utility is often limit by the $O(knd^2)$ computational bottleneck.…

Machine Learning · Computer Science 2026-01-29 Boyu Liu , Lianke Qin , Zhao Song , Yitan Wang , Jiale Zhao

In numerous settings, agents lack sufficient data to directly learn a model. Collaborating with other agents may help, but it introduces a bias-variance trade-off, when local data distributions differ. A key challenge is for each agent to…

Machine Learning · Computer Science 2025-02-20 Franco Galante , Giovanni Neglia , Emilio Leonardi

Principal components analysis (PCA) is a standard tool for identifying good low-dimensional approximations to data in high dimension. Many data sets of interest contain private or sensitive information about individuals. Algorithms which…

Machine Learning · Statistics 2013-08-09 Kamalika Chaudhuri , Anand D. Sarwate , Kaushik Sinha

Many applications of machine learning, such as human health research, involve processing private or sensitive information. Privacy concerns may impose significant hurdles to collaboration in scenarios where there are multiple sites holding…

Machine Learning · Computer Science 2021-02-24 Hafiz Imtiaz , Jafar Mohammadi , Anand D. Sarwate

Recent advances have sparked significant interest in the development of privacy-preserving Principal Component Analysis (PCA). However, many existing approaches rely on restrictive assumptions, such as assuming sub-Gaussian data or being…

Methodology · Statistics 2025-07-22 Minwoo Kim , Sungkyu Jung

We study distributed big-data nonconvex optimization in multi-agent networks. We consider the (constrained) minimization of the sum of a smooth (possibly) nonconvex function, i.e., the agents' sum-utility, plus a convex (possibly) nonsmooth…

Optimization and Control · Mathematics 2018-09-03 Ivano Notarnicola , Ying Sun , Gesualdo Scutari , Giuseppe Notarstefano

We study optimization algorithms for the finite sum problems frequently arising in machine learning applications. First, we propose novel variants of stochastic gradient descent with a variance reduction property that enables linear…

Machine Learning · Computer Science 2017-07-06 Jakub Konečný

With artificial intelligence systems becoming ubiquitous in our society, its designers will soon have to start to consider its social dimension, as many of these systems will have to interact among them to work efficiently. With this in…

Artificial Intelligence · Computer Science 2020-06-23 Santiago Cuervo , Marco Alzate

This paper considers a distributed multi-agent optimization problem, with the global objective consisting of the sum of local objective functions of the agents. The agents solve the optimization problem using local computation and…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-11-07 Shripad Gade , Nitin H. Vaidya

We consider an online estimation problem involving a set of agents. Each agent has access to a (personal) process that generates samples from a real-valued distribution and seeks to estimate its mean. We study the case where some of the…

Machine Learning · Computer Science 2022-12-20 Mahsa Asadi , Aurélien Bellet , Odalric-Ambrym Maillard , Marc Tommasi

Nowadays, more and more datasets are stored in a distributed way for the sake of memory storage or data privacy. The generalized eigenvalue problem (GEP) plays a vital role in a large family of high-dimensional statistical models. However,…

Machine Learning · Computer Science 2021-11-25 Kexin Lv , Fan He , Xiaolin Huang , Jie Yang , Liming Chen

This paper presents a novel distributed formulation of the min-max optimization problem. Such a formulation enables enhanced flexibility among agents when optimizing their maximization variables. To address the problem, we propose two…

Optimization and Control · Mathematics 2025-05-19 Runze You , Kun Huang , Shi Pu

Existing large-scale optimization schemes are challenged by both scalability and cyber-security. With the favorable scalability, adaptability, and flexibility, decentralized and distributed optimization paradigms are widely adopted in…

Optimization and Control · Mathematics 2020-12-23 Xiang Huo , Mingxi Liu

Decentralized optimization has become a standard paradigm for solving large-scale decision-making problems and training large machine learning models without centralizing data. However, this paradigm introduces new privacy and security…

Machine Learning · Computer Science 2024-08-19 Changxin Liu , Nicola Bastianello , Wei Huo , Yang Shi , Karl H. Johansson

The statistical analysis of massive and complex data sets will require the development of algorithms that depend on distributed computing and collaborative inference. Inspired by this, we propose a collaborative framework that aims to…

Statistics Theory · Mathematics 2015-07-02 Gérard Biau , Kevin Bleakley , Benoit Cadre

Eigenspace estimation is fundamental in machine learning and statistics, which has found applications in PCA, dimension reduction, and clustering, among others. The modern machine learning community usually assumes that data come from and…

Machine Learning · Statistics 2023-06-28 Xiao Guo , Xiang Li , Xiangyu Chang , Shusen Wang , Zhihua Zhang

We consider the problem of solving a large-scale system of linear equations in a distributed or federated manner by a taskmaster and a set of machines, each possessing a subset of the equations. We provide a comprehensive comparison of two…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-24 Boris Velasevic , Rohit Parasnis , Christopher G. Brinton , Navid Azizan

We study a collaborative revenue management problem where multiple decentralized parties agree to share some of their capacities. This collaboration is performed by constructing a large mathematical programming model available to all…

Optimization and Control · Mathematics 2021-12-30 Utku Karaca , S. Ilker Birbil , Nursen Aydin , Gizem Mullaoglu

In this paper we derive and analyze two algorithms -- referred to as decentralized power method (DPM) and decentralized Lanczos algorithm (DLA) -- for distributed computation of one (the largest) or multiple eigenvalues of a sample…

Distributed, Parallel, and Cluster Computing · Computer Science 2013-03-29 Federico Penna , Slawomir Stanczak

We study distributed multi-agent large-scale optimization problems, wherein the cost function is composed of a smooth possibly nonconvex sum-utility plus a DC (Difference-of-Convex) regularizer. We consider the scenario where the dimension…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-05-29 Ivano Notarnicola , Ying Sun , Gesualdo Scutari , Giuseppe Notarstefano