Upcoming Events

Princeton University is actively monitoring the situation around coronavirus (COVID-19) and the evolving guidance from government and health authorities. The latest guidance for Princeton members and visitors is available on the University’s Emergency Management website. 

No upcoming events found.

Subscribe to Events | More RSS feeds

Events Archive

Can learning theory resist deep learning?

Can learning theory resist deep learning?
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 practice, with a stream of algorithms that exhibit both good empirical performance on real-world...
Location: CS 105
Speaker(s):
Francis Bach
INRIA
Tags: CSML Seminar Series

Machine Learning for the Sciences

Machine Learning for the Sciences

Taking place every other Friday. Lunch will be provided.

Location: 26 Prospect Ave, Auditorium 103
Tags: ML for the Sciences

Convergence Rates of Stochastic Algorithms in Nonsmooth Nonconvex Optimization

Convergence Rates of Stochastic Algorithms in Nonsmooth Nonconvex Optimization
Stochastic iterative methods lie at the core of large-scale optimization and its modern applications to data science. Though such algorithms are routinely and successfully used in practice on highly irregular problems (e.g. deep neural networks), few performance guarantees are available outside of smooth or convex settings. In this talk, I will...
Location: B205 Engineering Quadrangle
Speaker(s):
Dmitriy Drusvyatskiy
University of Washington
Convergence Rates of Stochastic Algorithms in Nonsmooth Nonconvex Optimization
Tags: CSML Seminar Series

Exploration by Optimization in Partial Monitoring

Exploration by Optimization in Partial Monitoring

In many real-world problems learners cannot directly observe their own rewards but can still infer whether some particular action is successful. How should a learner take actions to balance its need of information while maximizing their reward in this setting? Partial monitoring is a framework introduced a few decades ago to model learning...

Location: Sherrerd 101
Speaker(s):
Csaba Szepesvari
Professor of Computing Science, University of Alberta
Tags: CSML Seminar Series

Randomized Methods for Low-Rank Tensor Decomposition in Unsupervised Learning

Randomized Methods for Low-Rank Tensor Decomposition in Unsupervised Learning
Tensor decomposition discovers latent structure in higher-order data sets and is the higher-order analogue of the matrix decomposition.
Location: 214 Fine Hall
Speaker(s):
Tamara Kolda
Sandia National Laboratories
Tags: CSML Seminar Series

Algorithm and Statistical Inference for Recovery of Discrete Structure

Algorithm and Statistical Inference for Recovery of Discrete Structure
Discrete structure recovery is an important topic in modern high-dimensional inference. Examples of discrete structure include clustering labels, ranks of players, and signs of variables in a regression model.
Location: Sherrerd 101
Speaker(s):
Chao Gao
Assistant Professor, Statistics University of Chicago
Tags: CSML Seminar Series

Optimizing for Fairness in ML

Optimizing for Fairness in ML
Recent events have made evident the fact that algorithms can be discriminatory, reinforce human prejudices, accelerate the spread of misinformation, and are generally not as objective as they are widely thought to be.
Location: Sherrerd 101
Speaker(s):
Elisa Celis
Assistant Professor of Statistics and Data Science, Yale University
Tags: CSML Seminar Series

Machine Learning for the Sciences

Machine Learning for the Sciences

Taking place every other Friday. Lunch will be provided.

Location: 26 Prospect Ave, Auditorium 103
Tags: ML for the Sciences

Word Embeddings: What works, what doesn’t, and how to tell the difference for applied research

Word Embeddings: What works, what doesn’t, and how to tell the difference for applied research
We consider the properties and performance of word embeddings techniques in the context of political science research. In particular, we explore key parameter choices—including context window length, embedding vector dimensions and the use of pre-trained vs locally fit variants—with respect to efficiency and quality of inferences possible with...
Location: Corwin Hall, Room 127
Speaker(s):
Arthur Spirling
New York University
Tags: CSML Seminar Series

Machine Learning for the Sciences

Machine Learning for the Sciences

Taking place every other Friday. Lunch will be provided.

Location: 26 Prospect Ave, Auditorium 103
Tags: ML for the Sciences

Pages