Related papers: On the Limit Performance of Floating Gossip
In this paper, we present GossipGraD - a gossip communication protocol based Stochastic Gradient Descent (SGD) algorithm for scaling Deep Learning (DL) algorithms on large-scale systems. The salient features of GossipGraD are: 1) reduction…
Performative learning addresses the increasingly pervasive situations in which algorithmic decisions may induce changes in the data distribution as a consequence of their public deployment. We propose a novel view in which these…
We consider a network consisting of $n$ nodes connected in a ring formation and a source that generates updates according to a renewal process and disseminates them to the ring network according to a Poisson process. The nodes in the…
Federated learning has recently emerged as a paradigm promising the benefits of harnessing rich data from diverse sources to train high quality models, with the salient features that training datasets never leave local devices. Only model…
Emerging applications of machine learning in numerous areas involve continuous gathering of and learning from streams of data. Real-time incorporation of streaming data into the learned models is essential for improved inference in these…
This paper gives drastically faster gossip algorithms to compute exact and approximate quantiles. Gossip algorithms, which allow each node to contact a uniformly random other node in each round, have been intensely studied and been adopted…
Multi-simulator training has contributed to the recent success of Deep Reinforcement Learning by stabilizing learning and allowing for higher training throughputs. We propose Gossip-based Actor-Learner Architectures (GALA) where several…
Flow-based generative models, including diffusion models, excel at modeling continuous distributions in high-dimensional spaces. In this work, we introduce Flow Policy Optimization (FPO), a simple on-policy reinforcement learning algorithm…
We develop a learning-based control algorithm for unknown dynamical systems under very severe data limitations. Specifically, the algorithm has access to streaming and noisy data only from a single and ongoing trial. It accomplishes such…
Distributed dynamic gossip is a generalization of the classic telephone problem in which agents communicate to share secrets, with the additional twist that also telephone numbers are exchanged to determine who can call whom. Recent work…
In this paper, we show how the Federated Learning (FL) framework enables learning collectively from distributed data in connected robot teams. This framework typically works with clients collecting data locally, updating neural network…
Generative Flow Networks (GFlowNets) are powerful samplers for compositional objects that, by design, sample proportionally to a given non-negative reward. Nonetheless, in practice, they often struggle to explore the reward landscape…
Existing approaches in Federated Learning (FL) mainly focus on sending model parameters or gradients from clients to a server. However, these methods are plagued by significant inefficiency, privacy, and security concerns. Thanks to the…
Federated learning (FL) is a new paradigm for distributed machine learning that allows a global model to be trained across multiple clients without compromising their privacy. Although FL has demonstrated remarkable success in various…
Federated learning is an effective way of extracting insights from different user devices while preserving the privacy of users. However, new classes with completely unseen data distributions can stream across any device in a federated…
Permissionless blockchain environments necessitate the use of a fast and attack-resilient message propagation protocol for Block and Transaction messages to keep nodes synchronised and avoid forks. We present GossipSub, a gossip-based…
We study the problem of global maximization of a function f given a finite number of evaluations perturbed by noise. We consider a very weak assumption on the function, namely that it is locally smooth (in some precise sense) with respect…
Federated learning is an established method for training machine learning models without sharing training data. However, recent work has shown that it cannot guarantee data privacy as shared gradients can still leak sensitive information.…
Flow matching has recently emerged as a promising alternative to diffusion-based generative models, particularly for text-to-image generation. Despite its flexibility in allowing arbitrary source distributions, most existing approaches rely…
In this paper, we present an experimental analysis of the asynchronous push & pull rumour spreading protocol. This protocol is, to date, the best-performing rumour spreading protocol for simple, scalable, and robust information…