A review of distributed statistical inference
The rapid emergence of massive datasets in various fields poses a serious challenge to
traditional statistical methods. Meanwhile, it provides opportunities for researchers to …
traditional statistical methods. Meanwhile, it provides opportunities for researchers to …
Learning coefficient heterogeneity over networks: A distributed spanning-tree-based fused-lasso regression
Identifying the latent cluster structure based on model heterogeneity is a fundamental but
challenging task arises in many machine learning applications. In this article, we study the …
challenging task arises in many machine learning applications. In this article, we study the …
New scalable and efficient online pairwise learning algorithm
Pairwise learning is an important machine-learning topic with many practical applications.
An online algorithm is the first choice for processing streaming data and is preferred for …
An online algorithm is the first choice for processing streaming data and is preferred for …
Optimal convergence rates for distributed Nyström approximation
The distributed kernel ridge regression (DKRR) has shown great potential in processing
complicated tasks. However, DKRR only made use of the local samples that failed to capture …
complicated tasks. However, DKRR only made use of the local samples that failed to capture …
Optimal convergence rates for agnostic Nyström kernel learning
Nyström low-rank approximation has shown great potential in processing large-scale kernel
matrix and neural networks. However, there lacks a unified analysis for Nyström …
matrix and neural networks. However, there lacks a unified analysis for Nyström …
Towards understanding ensemble distillation in federated learning
Federated Learning (FL) is a collaborative machine learning paradigm for data privacy
preservation. Recently, a knowledge distillation (KD) based information sharing approach in …
preservation. Recently, a knowledge distillation (KD) based information sharing approach in …
Effective distributed learning with random features: Improved bounds and algorithms
In this paper, we study the statistical properties of distributed kernel ridge regression
together with random features (DKRR-RF), and obtain optimal generalization bounds under …
together with random features (DKRR-RF), and obtain optimal generalization bounds under …
Distributed nyström kernel learning with communications
We study the statistical performance for distributed kernel ridge regression with Nyström
(DKRR-NY) and with Nyström and iterative solvers (DKRR-NY-PCG) and successfully derive …
(DKRR-NY) and with Nyström and iterative solvers (DKRR-NY-PCG) and successfully derive …
Optimal Rates for Agnostic Distributed Learning
The existing optimal rates for distributed kernel ridge regression (DKRR) often rely on a strict
assumption, assuming that the true concept belongs to the hypothesis space. However …
assumption, assuming that the true concept belongs to the hypothesis space. However …
Communication-Efficient Nonparametric Quantile Regression via Random Features
This article introduces a refined algorithm designed for distributed nonparametric quantile
regression in a reproducing kernel Hilbert space (RKHS). Unlike existing nonparametric …
regression in a reproducing kernel Hilbert space (RKHS). Unlike existing nonparametric …