B. Aditya
Prakash

General Information

Email:
badityap@cc.gatech.edu
Phone:
4048944663
Location - Building:
Coda
Location - Room:
S1207
Roles:
Professor (any rank)
Other
Primary Unit:
School of Computational Science and Engineering
Website URL
https://cc.gatech.edu/~badityap

Details

Degrees with subject and Postdoc Experience:
Degree Type
Ph.D.
Subject
Computer Science
Year
2012
Institution
Carnegie Mellon University
Location
Pittsburgh, PA
Degree Type
B.Tech
Subject
Computer Science and Engineering
Year
2007
Institution
Indian Institute of Technology - Bombay
Location
Mumbai, India
Statement of Research Interests:

I am broadly interested in Data Science, Machine Learning and AI with emphasis on solving big-data problems in networks and sequences. Many research questions I answer deal with understanding and managing efficiently, dynamical mechanisms (like propagation) on networks, occurring across natural, social and technological systems. These include problems motivated from public health, security, urban computing and the Web. My research combines theoretical analysis of models, developing efficient algorithms and empirical studies on large scale data.

Statement of Teaching Interests:

At Georgia Tech I had the opportunity to create multiple courses which have attracted students from across campus from Sciences, Engineering and Policy (apart from Computing), including professionals from the CDC pursuing GT degrees. I created a new graduate course ‘Data Science for Epidemiology’ and offered it for the first time in Fall 2020. I believe in ‘learning by doing’ and one of my goals was convincing the students that ML and AI are accessible to anyone, and they too can help make contributions to compelling real-world applications.

Selection of recent research, scholarly, and creative activities:

1. Tackling Time-Series Forecasting Generalization via Mitigating Concept Drift
Zhiyuan Zhao, Haoxin Liu, B. Aditya Prakash
in ICLR 2026, Rio de Janeiro

2. Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE
Guancheng Wan, Lucheng Fu, Haoxin Liu, Yiqiao Jin, Hui Yi Leong, Eric Hanchen Jiang, Hejia Geng, Jinhe Bi, Yunpu Ma, Xiangru Tang, B. Aditya Prakash, Yizhou Sun, Wei Wang
in ICLR 2026, Rio de Janeiro

3. TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level Effectiveness
Zhiyuan Zhao, Juntong Ni, Shangqing Xu, Haoxin Liu, Wei Jin, B. Aditya Prakash
in ICLR 2026, Rio de Janeiro

4. AHA: Scalable Alternative History Analysis for Operational Timeseries Applications
Harshavardhan Kamarthi, Harshil Shah, Henry Milner, Sayan Sinha, Yan Li, B. Aditya Prakash, Vyas Sekar
in ACM SIGKDD 2026, Jeju, Korea

5. Automatically Surfacing Opportunities for Improvements In Internet-Scale Applications
Vipul Harsh, Sayan Sinha, Henry Milner, Haijie Wu, B. Aditya Prakash, Vyas Sekar and Hui Zhang
in ACM HotNETS 2025, College Park