activity
20242026
collaborators

7 papers

cs.LG2026

A Joint-Distribution Route to Fair Representations with Continuous Sensitive Attributes

Yijin Ni, Xiaoming Huo

Fair representation learning with a continuous sensitive attribute requires a representation that is statistically independent of . Existing criteria, including generali…

stat.ME2026

Upper Confidence Bounds for the Prediction Error of Kernel Ridge Regression via Gaussian Refitting

Yijin Ni, Xiaoming Huo

Assessing a single model fit requires a computable upper confidence bound for the gap between the fit and the unknown truth, as mean estimates ignore realization variance. Standard…

stat.ML2026

Kernel Selection is Model Selection: A Unified Complexity-Penalized Approach for MMD Two-Sample Tests

Yijin Ni, Xiaoming Huo

The Maximum Mean Discrepancy (MMD) is a cornerstone statistic for nonparametric two-sample testing, but its test power is dictated entirely by the chosen kernel. Because any fixed…

cs.LG2026

Online Covariance Estimation in Averaged SGD: Improved Batch-Mean Rates and Minimax Optimality via Trajectory Regression

Yijin Ni, Xiaoming Huo

We study online covariance matrix estimation for Polyak--Ruppert averaged stochastic gradient descent (SGD). The online batch-means estimator of Zhu, Chen and Wu (2023) achieves an…

stat.ML2025

Kernel-based Equalized Odds: A Quantification of Accuracy-Fairness Trade-off in Fair Representation Learning

Yijin Ni, Xiaoming Huo

This paper introduces a novel kernel-based formulation of the Equalized Odds (EO) criterion, denoted as , for fair representation learning (FRL) in supervised settings. The c…

cs.LG2025

A Uniform Concentration Inequality for Kernel-Based Two-Sample Statistics

Yijin Ni, Xiaoming Huo

In many contemporary statistical and machine learning methods, one needs to optimize an objective function that depends on the discrepancy between two probability distributions. Th…