Alexander Rodríguez

Alexander Rodríguez
Ph.D. Candidate
School of Computational Science and Engineering
Georgia Institute of Technology

CODA Building S1349
756 W Peachtree St NW, Atlanta GA, 30308

CV: [PDF]

I am in the 2022-2023 academic job market for tenure-track positions.

I am a Ph.D. candidate in Computer Science at Georgia Tech, where I am fortunate to be advised by Prof. B. Aditya Prakash. I am interested in addressing technical challenges in machine learning and data mining motivated from disciplines facing pressing social needs, such as epidemiology and community resilience.

Our group is working several projects in response to the COVID pandemic. I'm leading our group's efforts in COVID forecasting with our model called DeepCOVID. Our forecasts are being featured by CDC and FiveThirtyEight. Check more details of our response to the pandemic at LINK.

Our research work on pandemic forecasting was awarded in several venues:

• Best paper award in AI4ABM workshop @ ICML 2022. Paper [PDF].
• 1st place (out of 35 global teams) in the COVID-19 Symptom Data Challenge (organized by Facebook/Catalyst Health/CMU). See winner announcement on Twitter [LINK], our talk at the winner's showcase [LINK], our white paper [PDF] and slides [PDF].
• 2nd place (out of 777 participants from 43 countries) in the C3AI COVID-19 Grand Challenge. See winner announcement on Twitter [LINK] and summary video [LINK].

Recent news:

• Feb. 2023: Presenting paper on epidemiologically-informed neural nets and tutorial on AI for data-centric epidemic forecasting.
• Jan. 2023: I'm visiting MIT and Boston University (Jan 4-14) to work in collaborations and connect with people. Feel free to ping me if you would like to meet in the Boston area.
• Nov. 2022: I was invited to give a research talk at the USC Viterbi School of Engineering.
• Sep. 2022: I was invited to participate in the HLF held in Heidelberg, Germany.
• Aug. 2022: [at KDD 2022] Gave a tutorial and co-organized a workshop [Tutorial] [Workshop].
• July 2022: Our work in differentiable agent-based models for epidemiology got the best paper award in the AI4ABM workshop @ ICML 2022.
• Nov. 2021: I was named a Rising Star in Data Science by the University of Chicago Data Science Institute (DSI) [LINK].
• Dec. 2021: Our group gave an invited workshop/tutorial for data-driven computational methods for disease forecasting by the Forecasting for Social Good Research Network to researchers and practitioners. [LINK].

Preprints: (under review)

Note: * denotes equal contribution.

1. Data-Centric Epidemic Forecasting: A Survey [arXiv]
   A. Rodríguez*, H. Kamarthi*, P. Agarwal, J. Ho, M. Patel, S. Sapre, and B.A. Prakash.

2. PROFHIT: Probabilistic Robust Forecasting for Hierarchical Time-series [arXiv]
   H. Kamarthi, L. Kong, A. Rodríguez, C. Zhang, B.A. Prakash

Selected publications:

1. Differentiable Agent-based Epidemiology [arXiv]
   A. Chopra*, A. Rodríguez*, J. Subramanian, A. Quera-Bofarull, B. Krishnamurthy, B.A. Prakash, R. Raskar
   International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023)

2. EINNs: Epidemiologically-Informed Neural Networks [arXiv]
   A. Rodríguez, J. Cui, N. Ramakrishnan, B. Adhikari, B.A. Prakash
   AAAI Conference on Artificial Intelligence (AAAI 2023)

3. Differentiable Agent-based Epidemiological Modeling for End-to-end Learning [arXiv]
   A. Chopra*, A. Rodríguez*, J. Subramanian, B. Krishnamurthy, B.A. Prakash, R. Raskar
   ICML 2022 Workshop AI for Agent-Based Modelling (AI4ABM @ ICML 2022). Oral presentation -- Best paper award.

4. Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the US [medRxiv]
   Estee Cramer, et al. [collaborative effort of the COVID-19 Forecast Hub]
   Proceedings of the National Academy of Sciences (PNAS). 2022.

5. Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future [arXiv]
   H. Kamarthi, A. Rodríguez, B.A. Prakash
   International Conference on Learning Representations (ICLR 2022)

6. CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting [arXiv]
   H. Kamarthi, L. Kong, A. Rodríguez, C. Zhang, B.A. Prakash
   The Web Conference (WebConf 2022)

7. When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting [arXiv]
   H. Kamarthi, L. Kong, A. Rodríguez, C. Zhang, B.A. Prakash
   Neural Information Processing Systems (NeurIPS 2021)

8. Steering a Historical Disease Forecasting Model Under a Pandemic: Case of Flu and COVID-19 [arXiv]
   A. Rodríguez*, N. Muralidhar*, B. Adhikari, A. Tabassum, N. Ramakrishnan, B.A. Prakash
   AAAI Conference on Artificial Intelligence (AAAI 2021)
   Shorter version in NeurIPS 2020 Machine Learning in Public Health (MLPH) Workshop

9. DeepCOVID: An Operational Deep Learning-driven Framework for Explainable Real-time COVID-19 Forecasting [medRxiv]
   A. Rodríguez, A. Tabassum, J. Cui, J. Xie, J. Ho, P. Agarwal, B. Adhikari, B.A. Prakash
   AAAI Conference on Innovative Applications of Artificial Intelligence (IAAI 2021)

10. Mapping Network States using Connectivity Queries [arXiv]
    Alexander Rodríguez, B. Adhikari, A. González, C.D. Nicholson, A. Vullikanti, B.A. Prakash
    IEEE International Conference on Big Data 2020 (IEEE BigData 2020)
    Shorter version in NeurIPS 2020 Artificial Intelligence and Humanitarian and Disaster Relief Workshop (AI + HADR @ NeurIPS 2020)

11. NetReAct: Interactive Learning for Network Summarization [arXiv]
    S.E. Amiri, B. Adhikari, J. Wenskovitch, A. Rodríguez, M. Dowling, C. North, B.A. Prakash
    NeurIPS 2020 Human And Machine in-the-Loop Evaluation and Learning Strategies Workshop (HAMLETS @ NeurIPS 2020)

12. Incorporating Expert Guidance in Epidemic Forecasting [arXiv]
    A. Rodríguez, B. Adhikari, N. Ramakrishnan, B.A. Prakash
    ACM SIGKDD 2020 Epidemiology Meets Data Mining and Knowledge Discovery Workshop (epiDAMIK @ KDD 2020)
    

Last update: Mar. 2023