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

Learning by Random Features: Sharp Asymptotics and Universality Laws

Wed, Dec 8, 2021, 4:30 pm
Many new random matrix ensembles arise in learning and modern signal processing. As shown in recent studies, the spectral properties of these matrices help answer crucial questions regarding the training and generalization performance of neural networks, and the fundamental limits of high-dimensional signal recovery. As a result, there has been...
Speaker(s):

What is Machine Learning and Can it Help Advance My Research?

Tue, Jan 11, 2022, 10:00 am
This Wintersession workshop aims to increase awareness of how machine learning could aid faculty, postdoc, and student research. No detailed prior knowledge of machine learning is assumed.
Speaker(s):

Introduction to Blockchain and Decentralized Finance

Tue, Jan 11, 2022, 1:00 pm

This is a two-part Princeton University Wintersession workshop January 11 and 13, 2022 from 1 p.m. to 3 p.m. in which Anchuri will discuss Bitcoin’s history and how it works. Anchuri will also feature in these workshops the rise of Ethereum, a programmable blockchain, and the type of applications that can be developed in the Ethereum ecosystem...

Speaker(s):

Introduction to NumPy

Tue, Jan 11, 2022, 2:00 pm

This Wintersession course covers the basics of NumPy, the package that underlies most scientific computing done in Python. It will explain the NumPy array, the principal data type in the NumPy package, and how it differs from similar Python structures like lists.

Speaker(s):

Data Visualization in Python

Wed, Jan 12, 2022, 1:00 pm to 4:00 pm
This Wintersession course provides an introduction to effective data visualization in Python. Several plotting packages will be discussed, including Matplotlib, Seaborn, and Plotly. Examples may include simple static 1D plots, 2D contour maps, heat maps, violin plots, and box plots. The session may also touch on more advanced interactive plots.
Speaker(s):

Introduction to Blockchain and Decentralized Finance

Thu, Jan 13, 2022, 1:00 pm

This is a two-part Princeton University Wintersession workshop January 11 and 13, 2022 from 1 p.m. to 3 p.m. in which Anchuri will discuss Bitcoin’s history and how it works. Anchuri will also feature in these workshops the rise of Ethereum, a programmable blockchain, and the type of applications that can be developed in the Ethereum ecosystem...

Speaker(s):

Machine Learning + Humanities Working Group

Wed, Jan 26, 2022, 12:30 pm

How can machine learning advance research in the humanities? What new challenges can humanities problems pose for machine learning? What insights can humanistic perspectives bring to bear upon the social and cultural dimensions of machine learning?

Machine Learning + Humanities Working Group

Wed, Feb 23, 2022, 12:30 pm

How can machine learning advance research in the humanities? What new challenges can humanities problems pose for machine learning? What insights can humanistic perspectives bring to bear upon the social and cultural dimensions of machine learning?

Machine Learning + Humanities Working Group

Wed, Mar 23, 2022, 12:30 pm

How can machine learning advance research in the humanities? What new challenges can humanities problems pose for machine learning? What insights can humanistic perspectives bring to bear upon the social and cultural dimensions of machine learning?

Machine Learning + Humanities Working Group

Wed, Apr 20, 2022, 12:30 pm

How can machine learning advance research in the humanities? What new challenges can humanities problems pose for machine learning? What insights can humanistic perspectives bring to bear upon the social and cultural dimensions of machine learning?

Pages

Events Archive

Bayesian Risk Optimization (BRO): A New Approach to Data-driven Stochastic Optimization

A large class of stochastic optimization problems involves optimizing an expectation taken with respect to an underlying distribution that is unknown in practice. One popular approach to addressing the distributional uncertainty, known as the distributionally robust optimization (DRO), is to hedge against the worst case among an ambiguity set of...
Location: Virtual Seminar
Speaker(s):

MCMC vs. Variational Inference -- for Credible Learning and Decision-Making at Scale

I will introduce some recent progress towards understanding the scalability of Markov chain Monte Carlo (MCMC) methods and their comparative advantage with respect to variational inference. I will discuss an optimization perspective on the infinite dimensional probability space, where MCMC leverages stochastic sample paths while variational...
Location: Zoom
Speaker(s):

Optimal No-Regret Learning in Repeated First-Price Auctions

First-price auctions have very recently swept the online advertising industry, replacing second-price auctions as the predominant auction mechanism on many platforms for display ads bidding. This shift has brought forth important challenges for a bidder: how should one bid in a first-price auction, where unlike in second-price auctions, it is no...
Speaker(s):

Machine Learning + Humanities Working Group

Join the new Machine Learning + Humanities Working Group for our second meeting of the semester on Wednesday, November 17. We’ll discuss the latest trends in research at the intersections of ML+Hum, and will look specifically at several projects including Machines Reading Maps from the Turing Institute and Newspaper Navigator from the Library of...

Scientific Visualization

Visualization enables insight, allows verification, and enhances presentations and publications. This workshop introduces the VisIt visualization software package, which has a graphical user interface for exploring and displaying data.  It can also produce animation to represent complex behavior of variables over time.

Speaker(s):

CITP Seminar: Matt Weinberg – A Crash Course on Algorithmic Mechanism Design

Matt is an assistant professor at Princeton University in the Department of Computer Science. His primary research interest is in Algorithmic Mechanism Design: algorithm design in settings where users have their own incentives. He is also interested more broadly in Algorithmic Game Theory, Algorithms Under Uncertainty, and Theoretical Computer...
Speaker(s):

From Shallow to Deep Representation Learning: Global Nonconvex Theory and Algorithms

In this talk, we consider two fundamental problems in signal processing and machine learning: (convolutional) dictionary learning and deep network training. For both problems, we provide the first global nonconvex landscape analysis of the learned representations, which will in turn provide new guiding principles for better model/architecture...
Location: Zoom - Register via Link in Body
Speaker(s):

CITP Seminar: Alex Hanna – Beyond Bias: Algorithmic Unfairness, Infrastructure, and Genealogies of Data

Problems of algorithmic bias are often framed in terms of lack of representative data or formal fairness optimization constraints to be applied to automated decision-making systems. However, these discussions sidestep deeper issues with data used in AI, including problematic categorizations and the extractive logics of crowdwork and data mining....
Location: Virtual Seminar
Speaker(s):

Machine Learning for Your Research

This workshop will give an overview of several modern supervised and unsupervised machine learning methods. We will discuss the advantages and limitations of each and explore what types of problems each is best suited to address.

Workshop format: Lecture and discussion

Location: Lewis Library 120
Speaker(s):

Learn about CSML’s graduate certificate program at info session

Graduate students from all departments are invited to attend an informal information session on the Center for Statistics and Machine Learning’s (CSML) graduate certificate program.

Location: Louis A. Simpson Lawn

Pages