Events

Upcoming Events

CSE DSI Machine Learning Seminar with Hongkai Zhao (Math, Duke University)

Hongkai Zhai will give a talk entitled Numerical understanding of neural networks: from representation to learning dynamics.

Are the measurement data enough: an instability study for an inverse problem for the stationary radiative transport near the diffusion limit

IMA Data Science Seminar

Hongkai Zhao (Duke University)

Peter O. Stahl Advanced Design Forum

The Stahl Forum aims to bring together industry leaders, government stakeholders, and academic researchers, to foster collaboration and sharing of data science, artificial intelligence, and machine learning best practices, to transform the ways in which chemicals and materials are designed, developed, and produced.

CSE DSI Machine Learning Seminar with Tianbao Yang (CSE, Texas A&M)

Tianbao Yang will give a talk entitled Beyond Adam: What Optimization Can Help Large Foundation Models.

Numerical Methods of Neural Network Discretization for Solving Nonlinear Differential Equations

IMA Data Science Seminar

Wenrui Hao (The Pennsylvania State University)

CSE DSI Machine Learning Seminar with Haihao (Sean) Lu (University of Chicago)

Haihao (Sean) Lu will give a talk entitled Constrained Continuous Optimization with First-Order Methods.

Past Events

CSE DSI Machine Learning Seminar with Hongkai Zhao (Math, Duke University)

Hongkai Zhai will give a talk entitled Numerical understanding of neural networks: from representation to learning dynamics.

Graph AI: Science and Industrial Applications

Industrial Problems Seminar 

Jie Chen (IBM Research)

Abstract

Graphs serve as both a mathematical abstraction and a structured framework for organizing data, finding widespread applications across scientific and technological domains. The ascent of graph neural networks underscores their exceptional efficacy in capturing intricate data interactions, leading to a resurgence of traditional applications with elevated solution quality and the emergence of novel uses. This talk delves into several graph-related challenges encountered in industrial contexts and the consequent evolution of graph-based deep learning methodologies. Topics include the learning of graph grammar for advancing material discovery and circuit design, the scaling of graph neural network training for financial forensics, and the unveiling of latent graph structures in power grid analytics. The talk concludes with a discussion on graph-based learning in the era of foundation models and research opportunities.

Conditional coalescent and its applications in population genomics

IMA Data Science Seminar

Wai-Tong (Louis) Fan (Indiana University)

CSE DSI Machine Learning Seminar with Renbo Zhao

Renbo Zhao (Business Analytics, University of Iowa) will speak on Frank-Wolfe-Type Methods for Minimizing Log-Homogenous Self-Concordant Barriers.

Academia, to Industry, to the NBA – Navigating a Non-Academic Career with a PhD

Industrial Problems Seminar 

Daniel Martens (Minnesota Timberwolves)

Advancing Machine-Learned Interatomic Potentials: Enhancing Accuracy and Robustness in Materials Science Applications

IMA Data Science Seminar

Yangshuai Wang (University of British Columbia)

CSE DSI Machine Learning Seminar with Zhengling Qi (Decision Sciences, GWU)

Zhengling Qi will give a talk entitled Policy Learning Methods for Confounded POMDPs.

Viva la Revolución of Open Source Large Language Models: Unleashing the Dark Horse in AI Innovation

Industrial Problems Seminar

Patrick Delaney (BloomBoard)

On small and large scales in training physics-informed neural networks for partial differential equations

IMA Data Science Seminar

Zhongqiang Zhang (Worcester Polytechnic Institute)

CSE DSI Machine Learning Seminar with James Zou (Biomedical DS, Stanford)

James Zou will give a talk entitled Scientific Innovations in the Age of Generative AI.