# Graduate Seminar

A seminar organized by/for the graduate students.

## Past Events › Graduate Seminar

### Events List Navigation

## Grad Student Seminar

Siyun Yu Server Allocation at Virtual Computing Labs via Queueing Models and Statistical Forecasting The Virtual Computing Lab (VCL) is a cloud computing service that provides users remote access to software applications. The main challenge is to decide how many servers should be preloaded with which applications, and how many servers should be left flexible, to be loaded with the requested application on demand. If a preloaded server with a desired application is available, the user gets immediate access. If…

Find out more »## Graduate Student Seminar: Jonathan Williams

Jonathan P. Williams UNC-Chapel Hill Non-penalized variable selection in high-dimensional linear model settings via generalized fiducial inference This is joint work with Jan Hannig Standard penalized methods of variable selection and parameter estimation rely on the magnitude of coefficient estimates to decide which variables to include in the final model. However, coefficient estimates are unreliable when the design matrix is collinear. To overcome this challenge an entirely new method of variable selection is presented within a generalized fiducial inference framework. …

Find out more »## Graduate seminar: Walt DeGrange, CANA Advisors

Walt DeGrange is a Principal Operations Research Analyst for CANA Advisors where he leads operations research analysis across federal and commercial domains. He is also a faculty member at the University of Arkansas in the Operations Management graduate program, a MBA Executive Practicum Advisor at the NC State University Supply Chain Resource Cooperative, a MORS Board of Director and the Chairperson for the INFORMS SpORts Section. His analytics projects include work with the Navy, Marine Corps, St Louis Blues (NHL),…

Find out more »## Graduate Seminar: Kelly Bodwin and John Palowitch

Kelly Bodwin and John Palowitch UNC-Chapel Hill Object-Set Testing Methods for Association Mining The exploratory mining of hidden, modular subgroups in complex systems is an ever-important task in our increasingly interconnected world. Go-to clustering approaches still involve classical methods like k-means, aggolmerative pairing, and latent-space modeling. These methods usually operate via an objective score of a partition of objects in the system under study: the higher the score, the stronger the "modularity" of the partition. In this talk, we present…

Find out more »## Grad Student Seminar: Yunxiao Liu

Yunxiao Liu UNC-Chapel Hill Semiparametric Inference of Integrated Volatility Functionals Using High-frequency Financial Data With the advent of intraday high-frequency data of financial assets since the late 1990s, the research of financial econometrics has entered into a “big data” era. New theoretical techniques using the theory of continuous time stochastic processes has been extensively developed, and new empirical evidence has been documented. In particular, due to its far-reaching applications in various fields such as risk management and option pricing, the…

Find out more »## Grad Student Seminar: Bryan Davis, Indeed.com

Bryan Gilbert Davis Indeed.com SEM Portfolio Optimization This talk will introduce the basic format and mechanisms of Search Engine Marketing and introduce the business motivations for its utilization. It will then delve into ongoing work at Indeed aimed at optimizing the distribution of budget over different queries, and will highlight the different modeling and engineering components of this work.

Find out more »## Grad Student Seminar: Hyungsuk Tak, SAMSI

Hyungsuk Tak SAMSI Bayesian Estimates of Astronomical Time Delays between Gravitationally Lensed Stochastic Light Curves The gravitational field of a galaxy can act as a lens and deflect the light emitted by a more distant object such as a quasar. Strong gravitational lensing causes multiple images of the same quasar to appear in the sky. Since the light in each gravitationally lensed image traverses a different path length from the quasar to the Earth, fluctuations in the source brightness are…

Find out more »## Grad Seminar: Wanyi Chen, Eric Friedlander

Wanyi Chen Dynamic Decision Making In A Queueing System With Secondary Service Motivated by operational practices in emergency departments, we consider a queueing model where each job is one of two types. Type 1 jobs need only a primary service given by a single server. Type 2 jobs need an additional secondary service. Secondary service is conducted by infinitely many servers. Primary servers cannot serve a new job until secondary service of a job is over. Jobs incur waiting costs…

Find out more »## Grad Student Seminar: Jianyu Liu and Zhengling Qi

Jianyu Liu Joint Skeleton Estimation of Multiple Directed Acyclic Graphs for Heterogeneous Population The directed acyclic graph (DAG) is a powerful tool to model the interactions of high-dimensional variables. While estimating edge directions in a DAG often requires interventional data, one can estimate the skeleton of a DAG (i.e., an undirected graph formed by removing the direction of each edge in a DAG) using observational data. In real data analyses, the samples of the high-dimensional variables may be collected from…

Find out more »## Grad Student Seminar: Tianxiao Sun & Jonathan Williams

Tianxiao Sun Globally convergent Newton-type methods for convex optimization based on smoothness structures We study the smooth structure of convex functions by generalizing a powerful concept so-called self-concordance introduced by Nesterov and Nemirovskii to a broader class of convex functions. The proposed theory provides a mathematical tool to analyze both local and global convergence of Newton-type methods as long as the underlying functionals fall into our generalized self-concordant function class. First, we introduce the class of generalized self-concordant functions, which…

Find out more »