中文
相关论文

相关论文: Byzantine-Robust Distributed Online Learning: Tami…

200 篇论文

In this paper, we propose a zeroth-order resilient distributed online algorithm for networks under Byzantine edge attacks. We assume that both the edges attacked by Byzantine adversaries and the objective function are time-varying.…

最优化与控制 · 数学 2025-11-10 Yuhang Liu , Wenjun Mei

We study the problem of non-constrained, discrete-time, online distributed optimization in a multi-agent system where some of the agents do not follow the prescribed update rule either due to failures or malicious intentions. None of the…

最优化与控制 · 数学 2022-04-12 Sourav Sahoo , Anand Gokhale , Rachel Kalpana Kalaimani

We consider the problem of distributed statistical machine learning in adversarial settings, where some unknown and time-varying subset of working machines may be compromised and behave arbitrarily to prevent an accurate model from being…

分布式、并行与集群计算 · 计算机科学 2017-10-24 Yudong Chen , Lili Su , Jiaming Xu

Byzantine robustness has received significant attention recently given its importance for distributed and federated learning. In spite of this, we identify severe flaws in existing algorithms even when the data across the participants is…

机器学习 · 计算机科学 2021-06-30 Sai Praneeth Karimireddy , Lie He , Martin Jaggi

We consider a distributed reinforcement learning setting where multiple agents separately explore the environment and communicate their experiences through a central server. However, $\alpha$-fraction of agents are adversarial and can…

机器学习 · 计算机科学 2022-06-02 Yiding Chen , Xuezhou Zhang , Kaiqing Zhang , Mengdi Wang , Xiaojin Zhu

Distributed multi-task learning provides significant advantages in multi-agent networks with heterogeneous data sources where agents aim to learn distinct but correlated models simultaneously.However, distributed algorithms for learning…

机器学习 · 计算机科学 2021-01-11 Jiani Li , Waseem Abbas , Xenofon Koutsoukos

In this paper, we investigate the problem of decentralized online resource allocation in the presence of Byzantine attacks. In this problem setting, some agents may be compromised due to external manipulations or internal failures, causing…

最优化与控制 · 数学 2026-05-27 Runhua Wang , Qing Ling , Hoi-To Wai , Zhi Tian

Adversarial attacks attempt to disrupt the training, retraining and utilizing of artificial intelligence and machine learning models in large-scale distributed machine learning systems. This causes security risks on its prediction outcome.…

密码学与安全 · 计算机科学 2021-09-07 Yusen Wu , Hao Chen , Xin Wang , Chao Liu , Phuong Nguyen , Yelena Yesha

In distributed learning systems, robustness issues may arise from two sources. On one hand, due to distributional shifts between training data and test data, the trained model could exhibit poor out-of-sample performance. On the other hand,…

机器学习 · 计算机科学 2022-11-01 Guanqiang Zhou , Ping Xu , Yue Wang , Zhi Tian

Distributed machine learning algorithms enable learning of models from datasets that are distributed over a network without gathering the data at a centralized location. While efficient distributed algorithms have been developed under the…

机器学习 · 计算机科学 2020-07-07 Zhixiong Yang , Waheed U. Bajwa

Distributed learning has become a promising computational parallelism paradigm that enables a wide scope of intelligent applications from the Internet of Things (IoT) to autonomous driving and the healthcare industry. This paper studies…

信号处理 · 电气工程与系统科学 2024-10-28 Yuhan Yang , Youlong Wu , Yuning Jiang , Yuanming Shi

Distributed learning has emerged as a leading paradigm for training large machine learning models. However, in real-world scenarios, participants may be unreliable or malicious, posing a significant challenge to the integrity and accuracy…

机器学习 · 计算机科学 2024-06-10 Grigory Malinovsky , Peter Richtárik , Samuel Horváth , Eduard Gorbunov

In this paper, we study a linear bandit optimization problem in a federated setting where a large collection of distributed agents collaboratively learn a common linear bandit model. Standard federated learning algorithms applied to this…

机器学习 · 计算机科学 2022-04-05 Ali Jadbabaie , Haochuan Li , Jian Qian , Yi Tian

This paper considers the problem of Byzantine fault tolerance in distributed linear regression in a multi-agent system. However, the proposed algorithms are given for a more general class of distributed optimization problems, of which…

机器学习 · 计算机科学 2019-04-05 Nirupam Gupta , Nitin H. Vaidya

In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures -- arbitrary and…

机器学习 · 计算机科学 2021-02-26 Dong Yin , Yudong Chen , Kannan Ramchandran , Peter Bartlett

While machine learning is going through an era of celebrated success, concerns have been raised about the vulnerability of its backbone: stochastic gradient descent (SGD). Recent approaches have been proposed to ensure the robustness of…

机器学习 · 统计学 2018-07-19 El Mahdi El Mhamdi , Rachid Guerraoui , Sébastien Rouault

In this paper, we propose a first-order distributed optimization algorithm that is provably robust to Byzantine failures-arbitrary and potentially adversarial behavior, where all the participating agents are prone to failure. We model each…

最优化与控制 · 数学 2022-07-27 Berkay Turan , Cesar A. Uribe , Hoi-To Wai , Mahnoosh Alizadeh

Distributed learning has become the standard approach for training large-scale machine learning models across private data silos. While distributed learning enhances privacy preservation and training efficiency, it faces critical challenges…

机器学习 · 计算机科学 2024-09-16 Changxin Liu , Yanghao Li , Yuhao Yi , Karl H. Johansson

Robust distributed learning algorithms aim to maintain reliable performance despite the presence of misbehaving workers. Such misbehaviors are commonly modeled as Byzantine failures, allowing arbitrarily corrupted communication, or as data…

机器学习 · 计算机科学 2025-10-17 Thomas Boudou , Batiste Le Bars , Nirupam Gupta , Aurélien Bellet

We study robust distributed learning that involves minimizing a non-convex loss function with saddle points. We consider the Byzantine setting where some worker machines have abnormal or even arbitrary and adversarial behavior. In this…

机器学习 · 计算机科学 2020-07-30 Dong Yin , Yudong Chen , Kannan Ramchandran , Peter Bartlett
‹ 上一页 1 2 3 10 下一页 ›