Predictive analytics is increasingly used to guide decision making in many applications. However, practice, we often have limited data on the true predictive task of interest and must instead rely more abundant a closely related proxy task. For example, e-commerce platforms use customer click (proxy) make product recommendations rather than relatively sparse purchase (true outcome interest); al...

We consider the problem of learning an unknown function f⋆ on d-dimensional sphere with respect to square loss, given i.i.d. samples {(yi,xi)}i≤n where xi is a feature vector uniformly distributed and yi=f⋆(xi)+εi. study two popular classes models that can be regarded as linearizations two-layers neural networks around random initialization: features model Rahimi–Recht (RF); tangent Jacot–Gabri...

This paper proposes a new test for change point in the mean of high-dimensional data based on spatial sign and self-normalization. The is easy to implement with no tuning parameters, robust heavy-tailedness theoretically justified both fixed-n sequential asymptotics under null alternatives, where n sample size. We demonstrate that provide better approximation finite distribution thus should be ...