4 papers
Is the regression -test doubly robust?
Lucy Xia, Oliver Y. Feng, Yang Feng +2
We study the robustness of the -test in random design linear models, and reach a somewhat nuanced conclusion. On the positive side, one of our main results is that the size of t…
Estimation of the sub-Gaussian Parameter
Jason Liu, Min Xu, Jinchuan Xing
The sub-Gaussian parameter (also called the variance proxy) of a mean-zero random variable is defined as where $L(λ) = \frac{2}{λ^2} \…
Learning the score under shape constraints
Rebecca M. Lewis, Oliver Y. Feng, Henry W. J. Reeve +2
Score estimation has recently emerged as a key modern statistical challenge, due to its pivotal role in generative modelling via diffusion models. Moreover, it is an essential ingr…
Optimal convex -estimation via score matching
Oliver Y. Feng, Yu-Chun Kao, Min Xu +1
In the context of linear regression, we construct a data-driven convex loss function with respect to which empirical risk minimisation yields optimal asymptotic variance in the dow…