Colloquium Series: Xinwei Shen

Our upcoming event for the Statistics Colloquium Series is scheduled for Monday, November 2nd from 12:00 – 1:00pm (ET) and will be an in-person presentation at Maxwell-Dworkin, Room 119. Lunch will be provided to guests following the talk. This week's speaker will be Xinwei Shen, Assistant Professor in the Department of Statistics at the University of Washington.

Fit Like a GLM, Sample Like a Generative Model

Abstract: Many scientific questions concern an entire conditional distribution rather than a conditional mean. Climate emulators should reproduce the variability, extremes and dependence of high-dimensional fields; species community models must capture richness and co-occurrence among multiple species. Classical tools such as density estimation and quantile regression are transparent but limited in flexibility and scale, while generative models such as GANs and diffusion models are powerful but computationally heavy and tuning-sensitive. We present engression, a distributional learning method that fits a generative model by minimizing a proper scoring rule, combining the simplicity of classical regression with the flexibility of modern machine learning. We show that engression yields temporally consistent, multivariate downscaling of regional climate models at a fraction of the cost of diffusion-based alternatives. For discrete outcomes, a continuous generator cannot produce valid values, and thresholding breaks gradient-based training. Generalized engression models (GEM) resolve this with data-type-specific links and a stochastic perturbation that smooths the loss, and enjoy universal representation guarantees. On a joint species distribution benchmark and mixed-type health data, GEM matches type-specific models on the marginals and improves on the joint distribution. This talk is based on arXiv:2307.00835, arXiv:2509.26258 and arXiv:2610.01823.

Speaker's Bio: Xinwei Shen is an Assistant Professor in the Department of Statistics at the University of Washington. She was a postdoctoral researcher at ETH Zürich working with Peter Bühlmann and Nicolai Meinshausen. She obtained her PhD at HKUST advised by Tong Zhang and a Bachelor of Science degree at Fudan University. Her current work focuses on distributional learning.