Tags: Colloquium Series

The Statistics Department hosts weekly colloquia on a variety of statistcal subjects, bringing in speakers from around the world.


Agus Sudjianto

Machine Learning for High-Risk Applications in Banking Renowned statistician George Box once famously stated, “All models are wrong, but some are useful.” In a world where machine learning increasingly automates important decisions about our lives, the consequences of model failures can be catastrophic. It’s critical to take deliberate steps to mitigate risk and avoid unintended harm.Evaluating the conceptual soundness of machine learning models…


2023 Clemson-UGA Joint Colloquium

Do statisticians have labs? Introduction to the Precision Medicine Artificial Intelligence Lab (PHAIR) Event Slides Abstract: In this talk, I discuss a non-traditional approach to statistics training through the use of a virtual lab structure. For over a decade, the Precision Health Artificial Intelligence lab gradually evolved from an informal meeting for a few students engaged in similar research topics to a large virtual lab with about 30…


Tuo Zhao

Approximation and Statistical Properties of Deep Neural Networks on Structured Data Abstract Deep neural networks have demonstrated remarkable generalization performance in high dimensional problems, e.g., image classification, where each image contains a large number of pixels. Such appealing performance contradicts a fundamental theoretical challenge – curse of data dimensionality. To explain this huge gap, we take the data intrinsic geometric…


Weijie Su

When Will You Become the Best Reviewer of Your Own Papers? A Truthful Owner-Assisted Scoring Mechanism Zoom Info Link: https://zoom.us/j/93936847707?pwd=ZWFVRWlqL0x1bWxNM2xMQTczb3lPQT09 Meeting ID: 939 3684 7707 Passcode: 821272 Abstract In 2014, NeurIPS received 1,678 paper submissions, while this number increased to 10,411 in 2022, putting a tremendous strain on the peer review process. In this talk, we attempt to address this challenge…


Nilanjan Chatterjee

Biography Dr. Nilanjan Chatterjee is a Bloomberg Distinguished Professor of Biostatistics and Genetic Epidemiology at Johns Hopkins University, with appointments in the Department of Biostatistics in the Bloomberg School of Public Health and in the Department of Oncology in the Sidney Kimmel Comprehensive Cancer Center in the Johns Hopkins School of Medicine. He was formerly…


Claire Donnat

Leveraging Horizontal and Vertical Network Structure Abstract The recent years have witnessed a surge in the amount of available structured data, typically modelled as a network capturing the relationships between different entities. This structure can either hold “horizontally” across features, or “vertically” across observations, and can be leveraged to considerably improve estimation - two aspects that we propose exploring throughout this…


Robert Mee

A Synthesis for Order-of-Addition Models Abstract: A wide variety of models have been proposed recently for experiments that vary the order in which components are added, or steps are performed. There are models with a linear effect of each component's position in the sequence, and models with added quadratic effects and product terms. Kriging models based on a component's position have also been proposed. Before models based on each component's…


Rebecca Steorts

Almost All of Entity Resolution Abstract Whether the goal is to estimate the number of people that live in a congressional district, to estimate the number of individuals that have died in an armed conflict, or to disambiguate individual authors using bibliographic data, all these applications have a common theme—integrating information from multiple sources. Before such questions can be answered, databases must be cleaned and integrated in a…


Georgios Fellouris

Sequential multiple testing  Abstract In this talk we will consider the multiple testing problem when theobservationsare collected in real time over multiple data streams and the goal isto decide as quickly as possible. In this context, a multiple testingprocedure consists of not only a decision rule but also a stopping rule.We will present such pairs that minimize asymptoticallythe expected time for decision, uniformly with respect to the…


Jyotishka Datta

Recent Developments in Bayesian Shrinkage for Sparse and Structured Data Abstract Sparse signal recovery remains an important challenge in large scale data analysis and global-local (G-L) shrinkage priors have undergone an explosive development in the last decade in both theory and methodology. These developments have established the G-L priors as the state-of-the-art Bayesian tool for sparse signal recovery. In the first part of my talk, I will…
Subscribe to Colloquium Series