As a result, it tractably draws samples even when the matrices forming the Khatri-Rao product have tens of millions of rows each.

Unfortunately, these theoretical results cannot well explain the empirical successes of deep learning well, as they require the model size tobenolargerthan O(n)(thegeneralization boundsbecomevacuousotherwise).

It enjoys model-free coverage guarantee regardless of the underlying distribution of the data.

Bilinear bandits (Jun et al., 2019; Lu et al., 2021; Kang et al., 2022) are an important class of