Scholar
Harshavardhan Kamarthi
Google Scholar ID: LNXEjT8AAAAJ
Georgia Institute of Technology
Citations & Impact
Citations
473
H-index
13
i10-index
17
Publications
20
Co-authors
15
list available
Publications
Resume (English only)
Academic Achievements
- Publications:
- - Machine learning for data-centric epidemic forecasting (Nature Machine Intelligence, 2024)
- - Large Pre-Trained Time-series Models (NeurIPS 2024)
- - Learning Graph Structures and Uncertainty for Accurate and Calibrated Time-series Forecasting (UDM workshop at KDD 2024)
- - Large Scale Hierarchical Industrial Demand Time-Series Forecasting incorporating Sparsity (KDD 2024)
Research Experience
- Machine Learning PhD student focusing on time-series forecasting research.
Education
- - PhD in Computational Science and Engineering, Georgia Institute of Technology, Advisor: Dr. B Aditya Prakash
- - Graduated from Indian Institute of Technology Madras, fortunate to have worked with Dr. Balaraman Ravindran and Dr. Sutanu Chakraborti
Background
- Research interests broadly revolve around robust time-series forecasting analysis with a focus on uncertainty, scalability, and cross-domain generalization. Current research interests include:
- - Foundational time-series models pretrained on multiple domain datasets and generalizable across a wide range of domains and tasks.
- - Scalable and efficient time-series forecasting models that can handle large-scale time-series data and provide robust and calibrated forecasts.
- - Probabilistic time-series forecasting models that can provide uncertainty estimates and are robust to outliers, missing data, and novel scenarios.
Miscellany
- Released Samaya, an easy-to-use library for time-series foundational models.
