Distributed learning with regularized least squares

SB Lin, X Guo, DX Zhou - Journal of Machine Learning Research, 2017 - jmlr.org
We study distributed learning with the least squares regularization scheme in a reproducing
kernel Hilbert space (RKHS). By a divide-and-conquer approach, the algorithm partitions a …

Distributed kernel-based gradient descent algorithms

SB Lin, DX Zhou - Constructive Approximation, 2018 - Springer
We study the generalization ability of distributed learning equipped with a divide-and-
conquer approach and gradient descent algorithm in a reproducing kernel Hilbert space …

Online pairwise learning algorithms

Y Ying, DX Zhou - Neural computation, 2016 - ieeexplore.ieee.org
Pairwise learning usually refers to a learning task that involves a loss function depending on
pairs of examples, among which the most notable ones are bipartite ranking, metric learning …

Rates of convergence of randomized Kaczmarz algorithms in Hilbert spaces

X Guo, J Lin, DX Zhou - Applied and Computational Harmonic Analysis, 2022 - Elsevier
Abstract Recently, the Randomized Kaczmarz algorithm (RK) draws much attention because
of its low computational complexity and less requirement on computer memory. Many …

Optimal convergence for distributed learning with stochastic gradient methods and spectral algorithms

J Lin, V Cevher - Journal of Machine Learning Research, 2020 - jmlr.org
We study generalization properties of distributed algorithms in the setting of nonparametric
regression over a reproducing kernel Hilbert space (RKHS). We first investigate distributed …

Online learning algorithms can converge comparably fast as batch learning

J Lin, DX Zhou - IEEE transactions on neural networks and …, 2017 - ieeexplore.ieee.org
Online learning algorithms in a reproducing kernel Hilbert space associated with convex
loss functions are studied. We show that in terms of the expected excess generalization …

Self-paced learning-assisted regularization reconstruction method with data-adaptive prior for electrical capacitance tomography

J Lei, Q Liu - Expert Systems with Applications, 2022 - Elsevier
The advent of electrical capacitance tomography provides a potential visualization-based
measurement paradigm for process monitoring, but the large gap between the reconstructed …

Convergence of gradient descent for minimum error entropy principle in linear regression

T Hu, Q Wu, DX Zhou - IEEE Transactions on Signal Processing, 2016 - ieeexplore.ieee.org
We study the convergence of minimum error entropy (MEE) algorithms when they are
implemented by gradient descent. This method has been used in practical applications for …

[HTML][HTML] Analysis of regularized federated learning

L Liu, DX Zhou - Neurocomputing, 2025 - Elsevier
Federated learning is an efficient machine learning tool for dealing with heterogeneous big
data and privacy protection. Federated learning methods with regularization can control the …

Randomized Kaczmarz with tail averaging

EN Epperly, G Goldshlager, RJ Webber - arxiv preprint arxiv:2411.19877, 2024 - arxiv.org
The randomized Kaczmarz (RK) method is a well-known approach for solving linear least-
squares problems with a large number of rows. RK accesses and processes just one row at …