Skip to content

Author

Xiao-Fei Wu

We have 5 of 19 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Byzantine-Robust Sparse Regression with Missing Covariates

We study distributed sparse linear regression with missing covariates and Byzantine workers. Correcting for missing observations can make the regression loss nonconvex, while Byzantine reports can distort gradient updates and impair estimation. A communication-efficient method is proposed that combines robust gradient...

Xiao-Fei Wu, Rong-Mei Liang, Jian-Qing Shi · 0 citations
Preprint Aug 2026

A Prediction--Correction Analysis of Two-Way Block Splitting in Distributed Learning

This note revisits the convergence of the Parikh--Boyd two-way block-splitting algorithm for large-scale distributed learning through the He--Yuan prediction--correction framework and clarifies which algebraic initialization conditions allow the reduced implementation to inherit the full-space convergence and complexit...

Xiao-Fei Wu · 0 citations
Preprint Sep 2026

Heterogeneity-calibrated Byzantine-robust distributed composite quantile regression

The proposed heterogeneity-calibrated robust robust CQR (HC-RCQR) profiles local intercepts and calibrates scores using an approximate inverse profile Hessian, and establishes conditional contraction and support-recovery guarantees under suitable conditions.

Xiao-Fei Wu, Jian-Qing Shi · 0 citations
Preprint Aug 2026

Data-Driven Pinball-Loss Selection for Vertically Distributed Elastic-Net SVMs

A data-driven elastic-net support vector machine is proposed that learns simplex-constrained weights over candidate pinball losses while retaining one classifier, and a column-partitioned variable-splitting solver is developed.

Xiao-Fei Wu, Kai Qi, Rongmei Liang · 0 citations
Preprint Aug 2026

Distributed Stochastic Smoothing ADMM for Penalized Quantile Regression

A distributed stochastic smoothing alternating direction method of multipliers (DSS-ADMM) for horizontally partitioned penalized quantile regression, which characterize the scope of an extension to the minimax concave penalty and the smoothly clipped absolute deviation penalty.

Rongmei Liang, Xiao-Fei Wu · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.