相关论文: Resilience in Collaborative Optimization: Redundan…

Distributed optimization with open collaboration is a popular field since it provides an opportunity for small groups/companies/universities, and individuals to jointly solve huge-scale problems. However, standard optimization algorithms…

The celebrated result of Fischer, Lynch and Paterson is the fundamental lower bound for asynchronous fault tolerant computation: any 1-crash resilient asynchronous agreement protocol must have some (possibly measure zero) probability of not…

The goal of diagnosis is to compute good repair strategies in response to anomalous system behavior. In a decision theoretic framework, a good repair strategy has low expected cost. In a general formulation of the problem, the computation…

Both Byzantine resilience and communication efficiency have attracted tremendous attention recently for their significance in edge federated learning. However, most existing algorithms may fail when dealing with real-world irregular data…

In Federated Reinforcement Learning (FRL), agents aim to collaboratively learn a common task, while each agent is acting in its local environment without exchanging raw trajectories. Existing approaches for FRL either (a) do not provide any…

We study the convergence problem in fully asynchronous, uni-dimensional robot networks that are prone to Byzantine (i.e. malicious) failures. In these settings, oblivious anonymous robots with arbitrary initial positions are required to…

Our goal is to solve both problems of adverse selection and moral hazard for multi-agent projects. In our model, each selected agent can work according to his private "capability tree". This means a process involving hidden actions, hidden…

Recent works have shown that agents facing independent instances of a stochastic $K$-armed bandit can collaborate to decrease regret. However, these works assume that each agent always recommends their individual best-arm estimates to other…

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…

Communication-avoiding algorithms allow redundant computations to minimize the number of inter-process communications. In this paper, we propose to exploit this redundancy for fault-tolerance purpose. We illustrate this idea with QR…

We introduce and solve the problem of Byzantine fault tolerant distributed quickest change detection in both continuous and discrete time setups. In this problem, multiple sensors sequentially observe random signals from the environment and…

Recent advances in generative AI have enabled sophisticated multi-agent architectures for healthcare, where large language models power collaborative clinical decision-making. However, these distributed systems face critical challenges in…

Byzantine resilience emerged as a prominent topic within the distributed machine learning community. Essentially, the goal is to enhance distributed optimization algorithms, such as distributed SGD, in a way that guarantees convergence…

This paper studies distributed online learning under Byzantine attacks. The performance of an online learning algorithm is often characterized by (adversarial) regret, which evaluates the quality of one-step-ahead decision-making when an…

The success of machine learning (ML) has been intimately linked with the availability of large amounts of data, typically collected from heterogeneous sources and processed on vast networks of computing devices (also called {\em workers}).…

In a recent paper, Jaggi et al. (INFOCOM 2007), presented a distributed polynomial-time rate-optimal network-coding scheme that works in the presence of Byzantine faults. We revisit their adversarial models and augment them with three,…

Traditional resilient systems operate on fully-replicated fault-tolerant clusters, which limits their scalability and performance. One way to make the step towards resilient high-performance systems that can deal with huge workloads, is by…

Federated recommendation systems can provide good performance without collecting users' private data, making them attractive. However, they are susceptible to low-cost poisoning attacks that can degrade their performance. In this paper, we…

This paper presents a distributed continuous-time optimization framework aimed at overcoming the challenges posed by time-varying cost functions and constraints in multi-agent systems, particularly those subject to disturbances. By…

This paper investigates distributed zeroth-order feedback optimization in multi-agent systems with coupled constraints, where each agent operates its local action vector and observes only zeroth-order information to minimize a global cost…