Harshavardhan Kamarthi

I'm a Machine Learning Researcher and PhD student in Computer Science at Georgia Institute of Technology working on time-series analysis and uncertainty quantification. I previously did research at Indian Institute of Technology Madras working with Prof. Balaraman Ravindran and Prof. Milind Tambe on reinforcement learning and social networks.

My current research focuses on developing principled methods for time-series forecasting with a focus on uncertainty quantification, learning from multiple data sources and domains, and scaling to real-world applications. I work on applications in epidemiology, demand forecasting, and healthcare in collaboration with various organizations. I've developed novel probabilistic deep learning frameworks like EPIFNP for epidemic forecasting and STOIC for learning graph structures in multivariate time-series that provide well-calibrated uncertainty estimates.

I'm particularly interested in foundation models for time-series and developing pre-training approaches to leverage data across multiple domains. My recent work on LPTM (Large Pre-trained Time-series Models) introduces novel ways to handle heterogeneous time-series data during pre-training. I also work on making large language models more effective for time-series tasks through careful prompt engineering and adaptation techniques.

Publications

A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualization

A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualization

Haoxin Liu, Chenghao Liu, B. A. Prakash, Harshavardhan Kamarthi, Lingkai Kong, Zhiyuan Zhao, Chao Zhang, Aditya Prakash, Shangqing Xu, Aditya B. Sasanur, Megha Sharma, Jiaming Cui, Qingsong Wen, Jindong Wang, Harshavardhan Kamarthi, Lst-prompt, Yong Liu, Tengge Hu, Haoran Zhang, Haixu Wu, Haoyu Lu, Wen Liu, Boxiang Zhang, Bing-Yi Wang, Kai Dong, Bo Liu, M. Mathis, Alexander E Webber, Tomás M León, Erin L Murray, Monica Sun, Lauren A White, Logan C Brooks, Alden Green, Addison J. Hu

arXiv.org 2024

ABSHTMLPDF

Machine learning for data-centric epidemic forecasting

Alexander Rodríguez, Harshavardhan Kamarthi, Pulak Agarwal, Javen Ho, Mira Patel, Suchet Sapre, B. A. Prakash

Nat. Mac. Intell. 2024

ABS

Evaluation of FluSight influenza forecasting in the 2021–22 and 2022–23 seasons with a new target laboratory-confirmed influenza hospitalizations

Sarabeth M Mathis, Alexander E Webber, Tomás M León, Erin L Murray, Monica Sun, Lauren A White, L. Brooks, Alden Green, Addison J. Hu, Roni Rosenfeld, Dmitry Shemetov, R. Tibshirani, D. J. McDonald, S. Kandula, Sen Pei, Rami Yaari, T. Yamana, Jeffery Shaman, Pulak Agarwal, Srikar Balusu, Gautham Gururajan, Harshavardhan Kamarthi, B. A. Prakash, Rishi Raman, Zhiyuan Zhao, Alexander Rodríguez, Akilan Meiyappan, Shalina Omar, P. Baccam, H. Gurung, B. Suchoski, Steve A Stage, M. Ajelli, A. G. Kummer, M. Litvinova, Paulo C. Ventura, Spencer Wadsworth, Jarad Niemi, Erica Carcelen, Alison L. Hill, Sara L. Loo, Clif McKee, Koji Sato, Clair Smith, S. Truelove, Sung-Mok Jung, J. Lemaitre, J. Lessler, Thomas McAndrew, Wenxuan Ye, N. Bosse, W. Hlavacek, Yen Ting Lin, A. Mallela, G. Gibson, Ye Chen, Shelby Lamm, Jaechoul Lee, Richard G Posner, A. Perofsky, C. Viboud, Leonardo Clemente, F. Lu, Austin G Meyer, Mauricio Santillana, Matteo Chinazzi, Jessica T. Davis, K. Mu, A. Pastore y Piontti, A. Vespignani, X. Xiong, Michal Ben-Nun, P. Riley, James Turtle, Chis Hulme-Lowe, Shakeel Jessa, V. Nagraj, Stephen D Turner, Desiree Williams, Avranil Basu, John M Drake, S. Fox, Ehsan Suez, Monica G. Cojocaru, Edward W. Thommes, E. Cramer, Aaron Gerding, A. Stark, E. Ray, N. Reich, Li Shandross, N. Wattanachit, Yijin Wang, Martha W Zorn, Majd Al Aawar, A. Srivastava, L. A. Meyers, A. Adiga, Benjamin Hurt, Gursharn Kaur, B. Lewis, M. Marathe, S. Venkatramanan, P. Butler, Andrew Farabow, Naren Ramakrishnan, N. Muralidhar, Carrie Reed, M. Biggerstaff, R. Borchering

Nature Communications 2024

ABSPDF
Learning Graph Structures and Uncertainty for Accurate and Calibrated Time-series Forecasting

Learning Graph Structures and Uncertainty for Accurate and Calibrated Time-series Forecasting

Harshavardhan Kamarthi, Lingkai Kong, Alexander Rodríguez, Chao Zhang, B. A. Prakash

arXiv.org 2024

ABSHTMLPDF
Large Scale Hierarchical Industrial Demand Time-Series Forecasting incorporating Sparsity

Large Scale Hierarchical Industrial Demand Time-Series Forecasting incorporating Sparsity

Harshavardhan Kamarthi, Aditya B. Sasanur, Xinjie Tong, Xingyu Zhou, James Peters, Joe Czyzyk, B. A. Prakash

Knowledge Discovery and Data Mining 2024

ABSHTMLPDF
Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning

Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning

Haoxin Liu, Harshavardhan Kamarthi, Lingkai Kong, Zhiyuan Zhao, Chao Zhang, B. A. Prakash

International Conference on Machine Learning 2024

ABSHTMLPDF
Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis

Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis

Haoxin Liu, Shangqing Xu, Zhiyuan Zhao, Lingkai Kong, Harshavardhan Kamarthi, Aditya B. Sasanur, Megha Sharma, Jiaming Cui, Qingsong Wen, Chao Zhang, B. A. Prakash

ABSHTMLPDF
LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting

LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting

Haoxin Liu, Zhiyuan Zhao, Jindong Wang, Harshavardhan Kamarthi, B. A. Prakash

Annual Meeting of the Association for Computational Linguistics 2024

ABSHTMLPDF

Evaluation of FluSight influenza forecasting in the 2021–22 and 2022–23 seasons with a new target laboratory-confirmed influenza hospitalizations

Sarabeth M Mathis, Alexander E Webber, Tomás M León, Erin L Murray, Monica Sun, L. A. White, L. Brooks, Alden Green, Addison J. Hu, D. J. McDonald, Roni Rosenfeld, Dmitry Shemetov, R. Tibshirani, S. Kandula, Sen Pei, Jeffrey Shaman, R. Yaari, T. Yamana, Pulak Agarwal, Srikar Balusu, Gautham Gururajan, Harshavardhan Kamarthi, B. A. Prakash, Rishi Raman, Alexander Rodríguez, Zhiyuan Zhao, Akilan Meiyappan, Shalina Omar, P. Baccam, H. Gurung, S. Stage, B. Suchoski, M. Ajelli, A. G. Kummer, M. Litvinova, Paulo C. Ventura, Spencer Wadsworth, Jarad Niemi, Erica Carcelen, Alison L. Hill, Sung-Mok Jung, J. Lemaitre, J. Lessler, Sara L. Loo, Clif McKee, Koji Sato, Clair Smith, S. Truelove, Thomas McAndrew, Wenxuan Ye, N. Bosse, W. Hlavacek, Yen Ting Lin, A. Mallela, Ye Chen, Shelby Lamm, Jaechoul Lee, Richard G Posner, A. Perofsky, Cécile Viboud, Leonardo Clemente, Fred Lu, Austin G Meyer, Mauricio Santillana, Matteo Chinazzi, Jessica T. Davis, K. Mu, A. Pastore y Piontti, A. Vespignani, X. Xiong, M. Ben-Nun, P. Riley, J. Turtle, Chis Hulme-Lowe, Shakeel Jessa, V. Nagraj, Stephen D Turner, Desiree Williams, Avranil Basu, John M Drake, S. Fox, G. Gibson, Ehsan Suez, E. Thommes, Monica G. Cojocaru, E. Cramer, Aaron Gerding, A. Stark, E. Ray, N. Reich, Li Shandross, N. Wattanachit, Yijin Wang, Martha W Zorn, Majd Al Aawar, A. Srivastava, L. A. Meyers, A. Adiga, Benjamin Hurt, Gursharn Kaur, Bryan L Lewis, M. Marathe, S. Venkatramanan, P. Butler, Andrew Farabow, N. Muralidhar, Naren Ramakrishnan, C. Reed, M. Biggerstaff, R. Borchering

medRxiv 2023

ABS
Large Pre-trained time series models for cross-domain Time series analysis tasks

Large Pre-trained time series models for cross-domain Time series analysis tasks

Harshavardhan Kamarthi, B. A. Prakash

arXiv.org 2023

ABSHTMLPDF
PEMS: Pre-trained Epidemic Time-series Models

PEMS: Pre-trained Epidemic Time-series Models

Harshavardhan Kamarthi, B. A. Prakash

arXiv.org 2023

ABSPDF

Uncertainty Quantification in Deep Learning

Lingkai Kong, Harshavardhan Kamarthi, Peng Chen, B. Prakash, Chao Zhang

Knowledge Discovery and Data Mining 2023

ABS

Epidemic Forecasting with a Data-Centric Lens

Alexander Rodríguez, Harshavardhan Kamarthi, B. Prakash

Knowledge Discovery and Data Mining 2022

ABS
Data-Centric Epidemic Forecasting: A Survey

Data-Centric Epidemic Forecasting: A Survey

Alexander Rodr'iguez, Harshavardhan Kamarthi, Pulak Agarwal, Javen Ho, Mira Patel, Suchet Sapre, B. Prakash

arXiv.org 2022

ABSPDF
When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting

When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting

Harshavardhan Kamarthi, Lingkai Kong, Alexander Rodr'iguez, Chao Zhang, B. Prakash

Knowledge Discovery and Data Mining 2022

ABSPDF
CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting

CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting

Harshavardhan Kamarthi, Lingkai Kong, Alexander Rodr'iguez, Chao Zhang, B. Prakash

The Web Conference 2021

ABSPDF
Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future

Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future

Harshavardhan Kamarthi, Alexander Rodr'iguez, B. Prakash

International Conference on Learning Representations 2021

ABSPDF
When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting

When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting

Harshavardhan Kamarthi, Lingkai Kong, Alexander Rodr'iguez, Chao Zhang, B. Prakash

Neural Information Processing Systems 2021

ABSPDF
Selective Intervention Planning using Restless Multi-Armed Bandits to Improve Maternal and Child Health Outcomes

Selective Intervention Planning using Restless Multi-Armed Bandits to Improve Maternal and Child Health Outcomes

Siddharth Nishtala, Lovish Madaan, Aditya Mate, Harshavardhan Kamarthi, Anirudh Grama, D. Thakkar, Dhyanesh Narayanan, S. Chaudhary, N. Madhiwalla, Ramesh Padmanabhan, A. Hegde, Pradeep Varakantham, Balaraman Ravindran, M. Tambe

arXiv.org 2021

ABSPDF
Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems

Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems

Aravind Venugopal, Elizabeth Bondi-Kelly, Harshavardhan Kamarthi, Keval Dholakia, Balaraman Ravindran, M. Tambe

Adaptive Agents and Multi-Agent Systems 2020

ABSPDF
Missed calls, Automated Calls and Health Support: Using AI to improve maternal health outcomes by increasing program engagement

Missed calls, Automated Calls and Health Support: Using AI to improve maternal health outcomes by increasing program engagement

Siddharth Nishtala, Harshavardhan Kamarthi, D. Thakkar, Dhyanesh Narayanan, Anirudh Grama, Ramesh Padmanabhan, N. Madhiwalla, S. Chaudhary, Balaraman Ravindran, Milind Tambe

arXiv.org 2020

ABSPDF
Integrating Lexical Knowledge in Word Embeddings using Sprinkling and Retrofitting

Integrating Lexical Knowledge in Word Embeddings using Sprinkling and Retrofitting

Aakash Srinivasan, Harshavardhan Kamarthi, Devi Ganesan, Sutanu Chakraborti

ICON 2019

ABSPDF
Learning policies for Social network discovery with Reinforcement learning

Learning policies for Social network discovery with Reinforcement learning

Harshavardhan Kamarthi, Priyesh Vijayan, Bryan Wilder, Balaraman Ravindran, Milind Tambe

arXiv.org 2019

Influence Maximization in Unknown Social Networks: Learning Policies for Effective Graph Sampling

Influence Maximization in Unknown Social Networks: Learning Policies for Effective Graph Sampling

Harshavardhan Kamarthi, Priyesh Vijayan, Bryan Wilder, Balaraman Ravindran, Milind Tambe

Adaptive Agents and Multi-Agent Systems 2019

ABSPDF
Hierarchical Genetic Algorithms with evolving objective functions

Hierarchical Genetic Algorithms with evolving objective functions

Harshavardhan Kamarthi, Kousik Krishnan

arXiv.org 2018

ABSPDF
Selective Intervention Planning using RMABs: Increasing Program Engagement to Improve Maternal and Child Health Outcomes

Selective Intervention Planning using RMABs: Increasing Program Engagement to Improve Maternal and Child Health Outcomes

Siddharth Nishtala, Lovish Madaan, Harshavardhan Kamarthi, Anirudh Grama, D. Thakkar, Dhyanesh Narayanan, S. Chaudhary, N. Madhiwalla, Ramesh Padmanabhan, A. Hegde, Pradeep Varakantham, Balaraman Ravindran, M. Tambe

Network discovery using Reinforcement Learning

Network discovery using Reinforcement Learning

Harshavardhan Kamarthi, Priyesh Vijayan, Bryan Wilder, Balaraman Ravindran, Milind Tambe