Harshavardhan Kamarthi
I’m Harsha. I’m a final-year Machine Learning PhD student in Department of Computational Science and Engineering at Georgia Institute of Technology . I am affiliated with AdityaLab and am advised by Dr. B Aditya Prakash. I graduated from Indian Institute of Technology Mardas and am fortunate to have worked with Dr. Balaraman Ravindran and Dr. Sutanu Chakraborti.
My research interests broadly revolves around robust time-series forecasting analysis with focus on uncertainty, scalability, and cross domain generalization. My current research interests include:
- Foundational time-series models that are prettrained on multiple domain datasets and generalizable across wide range of domains and tasks.(LPTM ‘24, PEMS ‘23, LstPrompt ‘24, TimeMMD ‘24).
- Scalable and efficient time-series forecasting models that can handle large-scale time-series data and provide robust and calibrated forecasts(HAILS ‘24, ProfHiT ‘23).
- Probabilistic time-series forecasting models that can provide uncertainty estimates and are robust to outliers, missing data and novel scenarios.(STOIC ‘23, CAMUL ‘22, EPIFNP ‘21, B2F ‘22).
news
Oct 1, 2024 | Large Pre-Traind Time-series Models is accepted at NeurIPS 2024! See you at Vancouver. |
---|---|
Sep 16, 2024 | Machine learning for data-centric epidemic forecasting will appear at Nature Machine Intelligence 6, 2024. Check out our survey on latest data-driven methods for epidemic forecasting. |
May 1, 2024 | Learning Graph Structures and Uncertainty for Accurate and Calibrated Time-series Forecasting on Graph leanring for probabilistic multivariate time-series forecasting to appear at UDM workshop at KDD 2024! |
Mar 1, 2024 | Large Scale Hierarchical Industrial Demand Time-Series Forecasting incorporating Sparsity on large-scale industrial demand hierarchical forecasting is accepted at KDD 2024! |
Feb 11, 2024 | LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting on zero-shot time-series forecasting using large language models is accepted at ACL Findings 2024! |