Theoretical Machine Learning Seminar

This talk focuses on a general phenomenon of "Frequency-Principle" that DNNs often fit target functions from low to high frequencies during the training. I will present empirical evidences on real datasets and deep networks of different settings as...

Minimax optimization, especially in its general nonconvex formulation, has found extensive applications in modern machine learning, in settings such as generative adversarial networks (GANs) and adversarial training. It brings a series of unique...

This talk discusses three aspects of deep learning from a statistical perspective: interpolation, optimality and sparsity. The first one attempts to interpret the double descent phenomenon by precisely characterizing a U-shaped curve within the...

Linear regression in L_p-norm is a canonical optimization problem that arises in several applications, including sparse recovery, semi-supervised learning, and signal processing. Standard linear regression corresponds to p=2, and p=1 or infinity is...

Modern machine learning often optimizes a nonconvex objective using simple algorithm such as gradient descent. One way of explaining the success of such simple algorithms is by analyzing the optimization landscape and show that all local minima are...

Understanding phenomena in systems of many interacting quantum particles, known as quantum many-body systems, is one of the most sought-after objectives in contemporary physics research. The challenge of simulating such systems lies in the extensive...