Previous Special Year Seminar

Nov
15
2019

Joint IAS/Princeton University Theoretical Machine Learning Seminar

Can learning theory resist deep learning?
Francis Bach
12:30pm|Princeton University, Computer Science - Room 105

Machine learning algorithms are ubiquitous in most scientific, industrial and personal domains, with many successful applications. As a scientific field, machine learning has always been characterized by the constant exchanges between theory and...

Nov
13
2019

Theoretical Machine Learning Seminar

Some Statistical Results on Deep Learning: Interpolation, Optimality and Sparsity
Guang Cheng
12:00pm|Dilworth Room

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...

Nov
12
2019

Theoretical Machine Learning Seminar

Fast IRLS Algorithms for p-norm regression
Sushant Sachdeva
12:00pm|White-Levy

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...

Oct
23
2019

Theoretical Machine Learning Seminar

Optimization Landscape and Two-Layer Neural Networks
Rong Ge
12:00pm|Dilworth Room

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...

Oct
22
2019

PCTS Seminar Series: Deep Learning for Physics

Autoregressive Simulation of Many-Body Quantum Systems
Or Sharir
2:00pm|*Princeton University, 407 Jadwin Hall, PCTS Seminar Room*

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...

Oct
22
2019

PCTS Seminar Series: Deep Learning for Physics

Machine Learning Techniques for Many-Body Quantum Systems
Giuseppe Carleo
11:45am|*Princeton University, 407 Jadwin Hall, PCTS Seminar Room*

In this introductory seminar I will cover the main machine learning techniques so-far adopted to study interacting quantum systems. I will first introduce the concept of neural-network quantum states [1], a representation of the many-body wave...