Related papers: Collaborative Learning in the Jungle (Decentralize…
This paper considers the multi-agent reinforcement learning (MARL) problem for a networked (peer-to-peer) system in the presence of Byzantine agents. We build on an existing distributed $Q$-learning algorithm, and allow certain agents in…
Decentralized learning has gained great popularity to improve learning efficiency and preserve data privacy. Each computing node makes equal contribution to collaboratively learn a Deep Learning model. The elimination of centralized…
We introduce the paradigm of validated decentralized learning for undirected networks with heterogeneous data and possible adversarial infiltration. We require (a) convergence to a global empirical loss minimizer when adversaries are…
Achieving agreement among distributed parties is a fundamental task in modern systems, underpinning applications such as consensus in blockchains, coordination in cloud infrastructure, and fault tolerance in critical services. However, this…
Blockchain technology offers a decentralized and secure method for storing and authenticating data, rendering it well-suited for various applications such as digital currencies, supply chain management, and voting systems. However, the…
Byzantine consensus is a classical problem in distributed computing. Each node in a synchronous system starts with a binary input. The goal is to reach agreement in the presence of Byzantine faulty nodes. We consider the setting where…
This paper studies Byzantine-robust stochastic optimization over a decentralized network, where every agent periodically communicates with its neighbors to exchange local models, and then updates its own local model by stochastic gradient…
Distributed learning has many computational benefits but is vulnerable to attacks from a subset of devices transmitting incorrect information. This paper investigates Byzantine-resilient algorithms in a decentralized setting, where devices…
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…
This paper considers the problem of detection in distributed networks in the presence of data falsification (Byzantine) attacks. Detection approaches considered in the paper are based on fully distributed consensus algorithms, where all of…
This paper explores the problem of reaching approximate consensus in synchronous point-to-point networks, where each pair of nodes is able to communicate with each other directly and reliably. We consider the mobile Byzantine fault model…
This paper addresses the problem of non-Bayesian learning over multi-agent networks, where agents repeatedly collect partially informative observations about an unknown state of the world, and try to collaboratively learn the true state. We…
Decentralized learning, which facilitates joint model training across geographically scattered agents, has gained significant attention in the field of signal and information processing in recent years. While the optimization errors of…
The cooperative bandit problem is increasingly becoming relevant due to its applications in large-scale decision-making. However, most research for this problem focuses exclusively on the setting with perfect communication, whereas in most…
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…
Much of the past work on asynchronous approximate Byzantine consensus has assumed scalar inputs at the nodes [3, 7]. Recent work has yielded approximate Byzantine consensus algorithms for the case when the input at each node is a…
This report contains two related sets of results with different assumptions on synchrony. The first part is about iterative algorithms in synchronous systems. Following our previous work on synchronous iterative approximate Byzantine…
Collaborative bandit learning, i.e., bandit algorithms that utilize collaborative filtering techniques to improve sample efficiency in online interactive recommendation, has attracted much research attention as it enjoys the best of both…
While the last few decades have witnessed a huge body of work devoted to inference and learning in distributed and decentralized setups, much of this work assumes a non-adversarial setting in which individual nodes---apart from occasional…
We study the gathering problem to make multiple agents initially scattered in arbitrary networks gather at a single node. There exist $k$ agents with unique identifiers (IDs) in the network, and $f$ of them are weakly Byzantine agents,…