Reduced rank approximation of matrices by Householder-Young methods is shown to be equivalent to fitting of a bilinear (multiplicative) model and to projection onto an optimally chosen subspace. The ...

We design a new provably efficient algorithm for episodic reinforcement learning with generalized linear function approximation. We analyze the algorithm under a new expressivity assumption that we ...

This paper offers a qualitative theoretical analysis of the error that may arise when a linear programming calculation is used to solve a problem involving some ...