Zheng HE

I am a PhD student in the Department of Computer Science at the University of British Columbia, advised by Prof. Danica J. Sutherland. I previously completed my M.Sc. (2023) and B.Eng. (2020) at Beihang University. In 2024, I was a visiting student at the Gatsby Computational Neuroscience Unit (UCL), collaborating with Prof. Arthur Gretton.

My research studies the statistical foundations of hypothesis testing. I develop principled methods for conditional independence testing, with a focus on understanding failure modes and providing robust guarantees in high-dimensional and online settings.

Broadly, I am interested in when and why learning algorithms succeed or break, and how to provide statistically grounded guarantees for complex, high-dimensional models. I am increasingly exploring how conditional invariance principles can improve robustness and interpretability in large-scale systems.

latest posts

Dec 10, 2025	Why testing conditional independence is so hard?
Nov 1, 2024	A note on kernel methods
Dec 30, 2023	A note on learning bounds
Feb 1, 2023	Learning with biased labels
Jul 12, 2022	Sparse double descent where network pruning aggravates overfitting

selected publications

On the Hardness of Conditional Independence Testing In Practice

Zheng He, Roman Pogodin, Yazhe Li, Namrata Deka, Arthur Gretton, and Danica J. Sutherland

In The Thirty-ninth Annual Conference on Neural Information Processing Systems, NeurIPS, 2025

Selected for spotlight presentation.

Abs arXiv Blog Poster Code

Tests of conditional independence (CI) underpin a number of important problems in machine learning and statistics, from causal discovery to evaluation of predictor fairness and out-of-distribution robustness. Shah and Peters (2020) showed that, contrary to the unconditional case, no universally finite-sample valid test can ever achieve nontrivial power. While informative, this result (based on "hiding" dependence) does not seem to explain the frequent practical failures observed with popular CI tests. We investigate the Kernel-based Conditional Independence (KCI) test - of which we show the Generalized Covariance Measure underlying many recent tests is nearly a special case - and identify the major factors underlying its practical behavior. We highlight the key role of errors in the conditional mean embedding estimate for the Type-I error, while pointing out the importance of selecting an appropriate conditioning kernel (not recognized in previous work) as being necessary for good test power but also tending to inflate Type-I error.
Sparse double descent: Where network pruning aggravates overfitting

Zheng He, Zeke Xie, Quanzhi Zhu, and Zengchang Qin

In International Conference on Machine Learning, ICML, 2022

Abs arXiv Blog Poster Code

People usually believe that network pruning not only reduces the computational cost of deep networks, but also prevents overfitting by decreasing model capacity. However, our work surprisingly discovers that network pruning sometimes even aggravates overfitting. We report an unexpected sparse double descent phenomenon that, as we increase model sparsity via network pruning, test performance first gets worse (due to overfitting), then gets better (due to relieved overfitting), and gets worse at last (due to forgetting useful information). While recent studies focused on the deep double descent with respect to model overparameterization, they failed to recognize that sparsity may also cause double descent. In this paper, we have three main contributions. First, we report the novel sparse double descent phenomenon through extensive experiments. Second, for this phenomenon, we propose a novel learning distance interpretation that the curve of l2 learning distance of sparse models (from initialized parameters to final parameters) may correlate with the sparse double descent curve well and reflect generalization better than minima flatness. Third, in the context of sparse double descent, a winning ticket in the lottery ticket hypothesis surprisingly may not always win.