Workshop Details

The DATA-INSPIRE TRIPODS Institute at Rutgers, in collaboration with the TRIPODS@Duke Institute and the TRIAD Institute at Georgia Tech, will host a one-day graduate student workshop on March 11, 2022 from 2pm to 5pm EST. The goal of this virtual event is to bring together graduate students from mathematics, computer science, statistics, and electrical engineering with interests in the foundational aspects of data science so that they can present their research, learn about research by others, and build their scientific networks. The event will also include an invited talk from Prof. Yao Xie, Georgia Institute of Technology. 

All graduate students are encouraged to submit a 5-7 minute talk to present during the event and a pdf poster. Following the talks, we will host an online poster session which will allow for further interactions among the graduate students and the TRIPODS Institutes faculty. If you would like to submit a talk and poster, please contact Lazaros Gallos at This email address is being protected from spambots. You need JavaScript enabled to view it. by March 1, 2022. 

The event is open to everyone interested in interdisciplinary research at the foundations of Data Science.

The event schedule is as follows:

2:00 - 2:15 pm  Introductions and Welcome

2:15 - 3:30 pm  Graduate student presentations 

Improving the Efficiency of Kinodynamic Planning with Machine Learning - Aravind Sivaramakrishnan

The ML4KP library: Integrating Machine Learning and Kinodynamic Motion Planning -Edgar Granados

Tame the combinatorial challenges in object rearrangement in confined spaces - Rui Wang

Fast High-Quality Tabletop Rearrangement in Bounded  Workspace - Kai Gao

Harmless interpolation in regression and classification with structured features - Andrew Mcrae

Conformal prediction for dynamic time-series - Chen Xu

Global Dynamics of Ramp Systems using DSGRN - Bernando Do Prado Rivas

ABCinML: Anticipatory Bias Correction in Machine Learning Applications - Aziz Almuzaini

3:30 - 4:20 pm Spatial-temporal point process modeling of discrete events data
Prof. Xie Yao, Georgia Tech
Discrete events are a sequence of observations consisting of event time, location, and possibly "marks" with additional event information. Such event data is ubiquitous in modern applications, including social networks, power networks, seismic activities, police reports data, neuronal spike trains, and COVID-19 data. We are particularly interested in capturing the complex dependence of the discrete events data, such as the latent influence -- triggering or inhibiting effects of the historical events on future events. I will present recent our research on this topic from the continuous-time and the discrete-time approaches and introduce computationally efficient model estimation procedures with statistical guarantees, leveraging the recent advances in variational inequality for monotone operators that bypass the difficulty posed by the original non-convex model estimation problem. The performance of the proposed method is illustrated using real-world data: crime, power outage, hospital ICU, and COVID-19 data 

4:20 - 5:00 pm  Poster session