We propose a new algorithm for the problem of recovering data that adheres to multiple, heterogeneous low-dimensional structures from linear observations.

We study lower bounds on adaptive sensing algorithms for recovering low rank matrices using linear measurements.

Protein inverse folding has attracted increasing attention in recent years.

Artificial neural networks are among the most successful modern machine learning methods, in particular because their non-linear parametrization provides a flexible way to implement feature learning (see, e.g., Goodfellow et al., 2016, chapter 15).

Many applications seek to recover low-rank approximations of noisy tensor data.

For example, HE uses secrets with small entries, and the HE community has considered standardizing small sparse secrets to improve efficiency and functionality.

On the theory side, most of the existing works have focused on algorithm design.

On the theory side, most of the existing works have focused on algorithm design.