Random initialization and implicit regularization in nonconvex statistical estimation
Recent years have seen a flurry of activities in designing provably efficient nonconvex procedures for solving statistical estimation / learning problems.
Learning Graph Inverse Problems with Geometric Neural Networks
Inverse Problems on graphs encompass many areas of physics, algorithms and statistics, and are a confluence of powerful methods, ranging from computational harmonic analysis and high-dimensional statistics to statistical physics.
Conventional light microscopes have been used for centuries for the study of small length scales down to about 250 nanometers. At such a resolution level images are blurred and noisy and the data often can be well approximated by a Gaussian or Poisson model.
