Related papers: Federated Heavy Hitter Recovery under Linear Sketc…
Federated Learning is a leading framework for training ML and AI models collaboratively across numerous user devices or databases. We study the trade-offs among estimation accuracy, privacy constraints, and communication cost for…
Edge devices can benefit remarkably from federated learning due to their distributed nature; however, their limited resource and computing power poses limitations in deployment. A possible solution to this problem is to utilize…
In this paper, we revisit the large-scale constrained linear regression problem and propose faster methods based on some recent developments in sketching and optimization. Our algorithms combine (accelerated) mini-batch SGD with a new…
The popular federated edge learning (FEEL) framework allows privacy-preserving collaborative model training via frequent learning-updates exchange between edge devices and server. Due to the constrained bandwidth, only a subset of devices…
We propose a randomized algorithm with quadratic convergence rate for convex optimization problems with a self-concordant, composite, strongly convex objective function. Our method is based on performing an approximate Newton step using a…
One of the major bottlenecks for efficient deployment of neural network based recommendation systems is the memory footprint of their embedding tables. Although many neural network based recommendation systems could benefit from the faster…
Federated learning alleviates the privacy risk in distributed learning by transmitting only the local model updates to the central server. However, it faces challenges including statistical heterogeneity of clients' datasets and resource…
Nonconvex sparse learning plays an essential role in many areas, such as signal processing and deep network compression. Iterative hard thresholding (IHT) methods are the state-of-the-art for nonconvex sparse learning due to their…
Federated representation learning (FRL) aims to learn personalized federated models with effective feature extraction from local data. FRL algorithms that share the majority of the model parameters face significant challenges with huge…
Federated learning protocols require repeated synchronization between clients and a central server, with convergence rates depending on learning rates, data heterogeneity, and client sampling. This paper asks whether iterative communication…
This work tackles the challenges of data heterogeneity and communication limitations in decentralized federated learning. We focus on creating a collaboration graph that guides each client in selecting suitable collaborators for training…
This paper focuses on reducing the communication cost of federated learning by exploring generalization bounds and representation learning. We first characterize a tighter generalization bound for one-round federated learning based on local…
Federated learning is a distributed machine learning approach to privacy preservation and two major technical challenges prevent a wider application of federated learning. One is that federated learning raises high demands on communication,…
Linear sketching algorithms have been widely used for processing large-scale distributed and streaming datasets. Their popularity is largely due to the fact that linear sketches can be naturally composed in the distributed model and be…
Federated learning~(FL) has recently attracted increasing attention from academia and industry, with the ultimate goal of achieving collaborative training under privacy and communication constraints. Existing iterative model averaging based…
We study classic streaming and sparse recovery problems using deterministic linear sketches, including l1/l1 and linf/l1 sparse recovery problems (the latter also being known as l1-heavy hitters), norm estimation, and approximate inner…
Federated Learning(FL) is a privacy-preserving machine learning paradigm where a global model is trained in-situ across a large number of distributed edge devices. These systems are often comprised of millions of user devices and only a…
Large-scale distributed training of neural networks is often limited by network bandwidth, wherein the communication time overwhelms the local computation time. Motivated by the success of sketching methods in sub-linear/streaming…
Modern cyber-physical architectures use data collected from systems at different physical locations to learn appropriate behaviors and adapt to uncertain environments. However, an important challenge arises as communication exchanges at the…
Many real-world matrix datasets arrive as high-throughput vector streams, making it impractical to store or process them in their entirety. To enable real-time analytics under limited computational, memory, and communication resources,…