The field of learning-augmented online algorithms has gained rapid prominence in recent years.

Submodular functions are heavily studied in a wide variety of disciplines since they are used to model many real world phenomena and are amenable to optimization.

A well-studied problem in machine learning and numerical linear algebra, with applications to recommendation systems, text mining, and computer vision, is that of computing a low-rank approximation of a matrix.

Submodular functions are heavily studied in a wide variety of disciplines since they are used to model many real world phenomena and are amenable to optimization.

Weighted sampling is a fundamental tool in data analysis and machine learning pipelines.

The massive instances occurring in modern-day applications can render existing algorithms prohibitively slow.

We develop a general framework for finding approximately-optimal preconditioners for solving linear systems.