Upcoming Events

No upcoming events found.

Subscribe to Events | More RSS feeds

Events Archive

Rethinking the Role of Optimization in Learning

Suriya Gunasekar
Rethinking the Role of Optimization in Learning
In this talk, I will overview our recent progress towards understanding how we learn large capacity machine learning models, especially deep neural networks. In the modern practice of deep learning, many successful models have far more trainable parameters compared to the number of training examples.
Location: B205 Engineering Quadrangle
Speaker(s):
Suriya Gunasekar
Toyota Technical Institute
Tags: Seminars

Astrophysics as a Testbed for Statistical Method Development

Dan Foreman-Mackey
Astrophysics as a Testbed for Statistical Method Development

There have been many efforts to apply methods from machine learning and statistics to make discoveries in astrophysics and throughout the physical sciences. While it is clear that the use of these methods has advanced our science goals, I will argue that these collaborations can also advance research in machine learning.

Location: Jadwin Hall Room 407, Princeton Center for Theoretical Science (PCTS)
Speaker(s):
Dan Foreman-Mackey
Center for Computational Astrophysics
Astrophysics as a Testbed for Statistical Method Development
Tags: Seminars

The Many Faces of Regularization: from Signal Recovery to Online Algorithms

Maryam Fazel
The Many Faces of Regularization: from Signal Recovery to Online Algorithms

In optimization, regularization plays several distinct roles. In the first part of the talk, we consider sample-efficient recovery of signals with low-dimensional structure, which is ill-posed without regularization.

Location: B205 Engineering Quadrangle
Speaker(s):
Maryam Fazel
University of Washington
The Many Faces of Regularization: from Signal Recovery to Online Algorithms
Tags: Seminars

Pages