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

Preconditioning Helps: Faster Convergence in Statistical and Reinforcement Learning

Mon, Apr 19, 2021, 4:30 pm
While exciting progress has been made in understanding the global convergence of vanilla gradient methods for solving challenging nonconvex problems in statistical estimation and machine learning, their computational efficacy is still far from satisfactory for ill-posed or ill-conditioned problems. In this talk, we discuss how the trick of...
Location: Virtual Seminar
Speaker(s):

CITP Reading Group: Recommender Systems (RS)

Tue, Apr 27, 2021, 4:00 pm

The goal of the recommender systems (RS) reading group is to gain deeper understanding both of seminal work as well as emerging ideas in the field. Papers will include research on RS algorithm development and evaluation; user-centered design and user studies for RS; fairness, accountability, and explainability in recommendations; and societal...

CSML Poster Session Event

Mon, May 3, 2021, 12:00 pm

The annual CSML Poster Session event will be held in person or virtually. Watch this space for further details.

Due date for independent work posters and papers TBA. Please check your email for details.

Princeton Research Day 2021

Thu, May 6, 2021 (All day)
Princeton’s celebration of early-career research and creative work is back in an all-online format.

Accelerate Your Code at the Princeton GPU Hackathon, June 2, 8-10, 2021

Wed, Jun 2, 2021, 8:00 am to Thu, Jun 10, 2021, 8:00 am

Graphics Processing Units (GPUs) offer high performance and massive parallelization, but learning how to program GPUs for scientific applications can be daunting.

Location: Virtual Seminarl

Events Archive

CITP Reading Group: Recommender Systems (RS)

The goal of the recommender systems (RS) reading group is to gain deeper understanding both of seminal work as well as emerging ideas in the field. Papers will include research on RS algorithm development and evaluation; user-centered design and user studies for RS; fairness, accountability, and explainability in recommendations; and societal...

DataX Workshop: Social biases in machine learning and in human nature: What social scientists and computer scientists can learn from each other

Princeton DataX Workshop: Social Biases in Machine Learning and in Human Nature: What Social Scientists and Computer Scientists Can Learn From Each Other:   

Speaker(s):

The One World Seminar on the Mathematics of Machine Learning

In this talk we study the problem of signal recovery for group models. More precisely for a given set of groups, each containing a small subset of indices, and for given linear sketches of the true signal vector which is known to be group-sparse in the sense that its support is contained in the union of a small number of these groups, we study...
Speaker(s):

Evnin Lecture Series: Calling BS: The Art of Skepticism in a Data-Driven World

Location: https://princeton.zoom.us/webinar/register/WN_ke10C34bQGeYENLqUANfYw

CITP Reading Group: Recommender Systems (RS)

The goal of the recommender systems (RS) reading group is to gain deeper understanding both of seminal work as well as emerging ideas in the field. Papers will include research on RS algorithm development and evaluation; user-centered design and user studies for RS; fairness, accountability, and explainability in recommendations; and societal...

Leveraging Dataset Symmetries in Neural Network Prediction

Scientists and engineers are increasingly applying deep neural networks (DNNs) to modelling and design of complex systems. While the flexibility of DNNs makes them an attractive tool, it also makes their solutions difficult to interpret and their predictive capability difficult to quantify.

Location: https://princeton.zoom.us/j/94658114530
Speaker(s):

Function Approximation via Sparse Random Fourier Features

Random feature methods have been successful in various machine learning tasks, are easy to compute, and come with theoretical accuracy bounds. They serve as an alternative approach to standard neural networks since they can represent similar function spaces without a costly training phase. However, for accuracy, random feature methods require more...

AI Meets Large-scale Sensing: preserving and exploiting structure of the real world to enhance machine perception

Machine capability has reached an inflection point, achieving human-level performance in tasks traditionally associated with cognition (vision, speech, strategic gameplay).  However, efforts to move such capability pervasively into the real world, have in many cases fallen far short of the relatively constrained and isolated demonstrations of...
Location: Virtual Seminar
Speaker(s):

Finite Width, Large Depth Neural Networks as Perturbatively Solvable Models

Abstract: Deep neural networks are often considered to be complicated "black boxes," for which a systematic analysis is not only out of reach but potentially impossible. In this talk, which is based on ongoing joint work with Dan Roberts and Sho Yaida, I will make the opposite claim. Namely, that deep neural networks at initialization are...

Location: https://princeton.zoom.us/j/94090634488
Speaker(s):

Computational Optics for Control and Readout of Neural Activity

Nearly all aspects of cognition and behavior require the coordinated action of multiple brain regions that are spread out over a large 3D volume. To understand the long-distance communication between these brain regions, we need optical techniques that can simultaneously monitor and control tens of thousands of individual neurons at cellular...
Speaker(s):

Pages