Communication-efficient online federated learning strategies for kernel regression
VC Gogineni, S Werner, YF Huang… - IEEE Internet of Things …, 2022 - ieeexplore.ieee.org
This article presents communication-efficient approaches to federated learning (FL) for
resource-constrained devices with access to streaming data. In particular, we first propose a …
resource-constrained devices with access to streaming data. In particular, we first propose a …
Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity
J Yang, S Ren - International Conference on Machine …, 2022 - proceedings.mlr.press
By integrating domain knowledge with labeled samples, informed machine learning has
been emerging to improve the learning performance for a wide range of applications …
been emerging to improve the learning performance for a wide range of applications …
Distributed Continual Learning with COCOA in High-dimensional Linear Regression
M Hellkvist, A Özçelikkale… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
We consider estimation under scenarios where the signals of interest exhibit change of
characteristics over time. In particular, we consider the continual learning problem where …
characteristics over time. In particular, we consider the continual learning problem where …
Decentralized Entropic Optimal Transport for Privacy-preserving Distributed Distribution Comparison
Privacy-preserving distributed distribution comparison measures the distance between the
distributions whose data are scattered across different agents in a distributed system and …
distributions whose data are scattered across different agents in a distributed system and …
The Effectiveness of Local Updates for Decentralized Learning under Data Heterogeneity
T Wu, Y Sun - arXiv preprint arXiv:2403.15654, 2024 - arxiv.org
We revisit two fundamental decentralized optimization methods, Decentralized Gradient
Tracking (DGT) and Decentralized Gradient Descent (DGD), with multiple local updates. We …
Tracking (DGT) and Decentralized Gradient Descent (DGD), with multiple local updates. We …
Decentralized Kernel Ridge Regression Based on Data-dependent Random Feature
Random feature (RF) has been widely used for node consistency in decentralized kernel
ridge regression (KRR). Currently, the consistency is guaranteed by imposing constraints on …
ridge regression (KRR). Currently, the consistency is guaranteed by imposing constraints on …