BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.2.3.1//EN TZID:America/New_York X-WR-TIMEZONE:America/New_York BEGIN:VEVENT UID:805@fds.yale.edu DTSTART;TZID=America/New_York:20241211T113000 DTEND;TZID=America/New_York:20241211T130000 DTSTAMP:20250916T142145Z URL:https://fds.yale.edu/events/fds-colloquium-guang-lin-purdue-towards-in terpretable-robust-trustworthy-machine-learning-for-diverse-applications-i n-science-and-engineering/ SUMMARY:FDS Colloquium: Guang Lin (Purdue)\, "Towards Interpretable\, Robus t Trustworthy Machine Learning for Diverse Applications in Science and Eng ineering"  DESCRIPTION:\n\n\n\n\nAbstract: This talk aims to create new technologies t hat can be translated into interpretable\, robust trustworthy AI systems t hat can be deployed for real-time complex dynamical system prediction\, an d applications to improve the stability and efficiency of complex dynamica l systems. In the first part of the talk\, I will employ Covid-19 pandemic prediction and personalized prediction in Alzheimer’s disease to illust rate how to build an interpretable\, trustworthy data-driven model. In the second part of the talk\, I will introduce scalable algorithms for Bayesi an deep learning via Repica exchange stochastic gradient Monte Carlo. Rep lica exchange Monte Carlo (reMC)\, also known as parallel tempering\, is a n important technique for accelerating the convergence of the conventional Markov Chain Monte Carlo (MCMC) algorithms. However\, such a method requi res the evaluation of the energy function based on the full dataset and is not scalable to big data. The naïve implementation of reMC in mini-batch settings introduces large biases\, which cannot be directly extended to t he stochastic gradient MCMC (SGMCMC)\, the standard sampling method for si mulating from deep neural networks (DNNs). In this talk\, I will present a n adaptive replica exchange SGMCMC (reSGMCMC) to automatically correct the bias and study the corresponding properties. The analysis implies an acce leration-accuracy trade-off in the numerical discretization of a Markov ju mp process in a stochastic environment. Empirically\, we test the algorith m through extensive experiments on various setups and obtain the state-of- the-art results on CIFAR10\, and CIFAR100 in both supervised learning and semi-supervised learning tasks. \n\n\n\nSpeaker bio: Prof. Guang Lin is t he Associate Dean for Research and Innovation and the Director of Data Sci ence Consulting Service that performs cutting-edge research on data scienc e and provides hands-on consulting support for data analysis and business analytics. He is also the Chair of the Initiative for Data Science and Eng ineering Applications at the College of Engineering. Guang Lin is also a F ull Professor in the School of Mechanical Engineering and Department of Ma thematics at Purdue University. \n\n\n\nLin received his Ph.D. from Brown University in 2007 and worked as a Research Scientist at DOE Pacific Nort hwest National Laboratory before joining Purdue in 2014. Prof. Lin has rec eived various awards\, such as the NSF CAREER Award\, Mid-Career Sigma Xi Award\, University Faculty Scholar\, College of Science Research Award\, M athematical \;Biosciences Institute Early Career Award\, and Ronald L. Brodzinski Award for Early Career Exception Achievement.\n CATEGORIES:FDS Events,Colloquium LOCATION:Yale Institute for Foundations of Data Science\, Kline Tower 13th Floor\, Room 1327\, New Haven\, CT\, 06511\, United States X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Kline Tower 13th Floor\, Ro om 1327\, New Haven\, CT\, 06511\, United States;X-APPLE-RADIUS=100;X-TITL E=Yale Institute for Foundations of Data Science:geo:0,0 END:VEVENT BEGIN:VTIMEZONE TZID:America/New_York X-LIC-LOCATION:America/New_York BEGIN:STANDARD DTSTART:20241103T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 TZNAME:EST END:STANDARD END:VTIMEZONE END:VCALENDAR