Statistics and Data Science Seminar

Department of Mathematics and Statistics




The Statistics & Data Science Seminar is hosted by the Department of Mathematics and Statistics and provides a weekly platform for academics and researchers from different domains to present and discuss problems and solutions regarding data collection, management and analysis.

Spring 2026 Seminars

Welcome to the Spring 2026 Seminar series! The seminar takes place on Wednesdays at 2 p.m. CT. The seminars will be hybrid (in-person and over Zoom) or virtual only (over Zoom). The location is Parker Hall 358. For any questions or requests, please contact Huan He or Haotian Xu. The list of speakers for this series can be found in the table below which is followed by information on the title and abstract of each talk.


Speaker Institution Date Format
    Feb. 4  
Sayar Karmakar U of Florida Feb. 11 In-person
    Feb. 18  
Jiajin Sun Florida State Feb. 25 In-person
Shuoyang Wang U of Louisville Mar. 4 In-person
NA NA Mar. 11 NA
Florian Gunsilius Emory Mar. 18 In-person
Yan Li Auburn Mar. 25 In-person
Rich Lehoucq   Sandia National Labs Apr. 1 In-person
Mine Dogucu  UC Irvine  Apr. 8  
    Apr. 15  
Shivam Kumar U Chicago  Apr. 22 In-Person 

 

Sayar Karmakar (U of Florida)

Title: Epidemic Changepoints: Applications in spatial anomaly detection and localizing LLM watermarks

 

Abstract: We present epidemic change-points as a unifying lens for two localization problems:(i) detecting spatial anomalies and (ii) segmenting watermarked regions in mixed-source text. For spatial data, we formalize a `spatial' change-point as an anomalous region (an epidemic in space), provide detection-accuracy results for single and multiple breaks, and propose a block-based scan that delivers substantial computational savings with guarantees. Next, we move to a seemingly unrelated but a very pertinent topic.


As large language models proliferate, ensuring content provenance has become a statistical challenge. For this problem on finding locLized modified text data segments, we introduce WISER, a fast epidemic-segmentation approach with finite-sample error bounds and consistency for multiple watermarked segments, and we demonstrate empirical gains over state-of-the-art baselines on benchmark datasets.


We emphasize how classical ​changepoint ideas ​catered to epidemic and transient departures yield principled, scalable solutions to modern problems in text provenance and spatial anomaly detection. Simulations and empirical studies corroborate the theory and point to open questions for PhD-level research.


Joint work with Soham Bonnerjee & Subhrajyoty Roy (watermarks) and with Soham Bonnerjee & George Michailidis (spatial anomaly)

Jiajin Sun (Florida State)

Title: 

Abstract:

Shuoyang Wang (U of Louisville)

Title: 

Abstract: 

Florian Gunsilius (Emory)

Title: 

Abstract: 

Yan Li (Auburn)

Title: 

Abstract: 

Rich Lehoucq (Sandia National Labs)

Title: Poisson tensor completion density estimator

Abstract: 

Mine Dogucu (UC Irvine)

Title: 

Abstract: 

Shivam Kumar (U Chicago)

Title: 

Abstract: