Subhro Das  Subhro Das photo         

contact information

Staff Research Scientist and Research Manager
MIT-IBM Watson AI Lab, IBM Research, Cambridge, MA, USA
  

links

Professional Associations

Professional Associations:  AAAI  |  ACM  |  IEEE  |  IEEE Signal Processing Society

more information

More information:  LinkedIn  |  Google Scholar  |  Webpage@CMU  |  Math Genealogy  |  Publons


2023

ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction
Wang Zhang, Tsui-Wei Weng, Subhro Das, Alexandre Megretski, Luca Daniel, Lam Nguyen
International Conference on Machine Learning (ICML), 2023

Reliable Gradient-free and Likelihood-free Prompt Tuning
Maohao Shen, Soumya Ghosh, Prasanna Sattigeri, Subhro Das, Yuheng Bu, Gregory Wornell
Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2023

Post-hoc Uncertainty Learning using a Dirichlet Meta-Model
Maohao Shen, Yuheng Bu, Prasanna Sattigeri, Soumya Ghosh, Subhro Das, Gregory Wornell
AAAI Conference on Artificial Intelligence (AAAI), 2023

Non-asymptotic System Identification for Linear Systems with Nonlinear Policies
Yingying Li, Tianpeng Zhang, Subhro Das, Jeff Shamma, Na Li
IFAC World Congress, 2023

Label-free Concept Bottleneck Models
Tuomas Oikarinen, Subhro Das, Lam M. Nguyen, Tsui-Wei Weng.
International Conference on Learning Representations (ICLR), 2023

Exact algorithms for learning to defer with half-spaces
Hussein Mozannar, Hunter Lang, Dennis Wei, Prasanna Sattigeri, Subhro Das, David Sontag
International Conference on Artificial Intelligence and Statistics (AISTATS), 2023


2022


Selective Regression Under Fairness Criteria
Abhin Shah, Yuheng Bu, Joshua Ka-Wing Lee, Prasanna Sattigeri, Rameswar Panda, Subhro Das, Gregory W. Wornell
International Conference on Machine Learning (ICML), 2022

On Convergence of Gradient Descent Ascent: A Tight Local Analysis
Haochuan Li, Farzan Farnia, Subhro Das, Ali Jadbabaie
International Conference on Machine Learning (ICML), 2022

Practical Skills Demand Forecasting via Representation Learning of Temporal Dynamics
Maysa Macedo, Wyatt Clarke, Eli Lucherini, Tyler Baldwin, Dilermando Queiroz, Rogerio de Paula, Subhro Das
Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (AIES), 2022

Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity
Jingzhao Zhang, Hongzhou Lin, Subhro Das, Suvrit Sra, Ali Jadbabaie
International Conference on Machine Learning (ICML), 2022

Evaluating Robustness of Cooperative MARL: A Model-based Approach
Nhan H. Pham, Lam M. Nguyen, Jie Chen, Hoang Thanh Lam, Subhro Das, Tsui-Wei Weng
arXiv preprint, arXiv:2202.03558, 2022


On observability and optimal gain design for distributed linear filtering and prediction
Subhro Das
Proceedings of the European Signal Processing Conference (EUSIPCO), 2022

GAT-GMM: Generative Adversarial Training for Gaussian Mixture Models
Farzan Farnia, William Wang, Subhro Das, Ali Jadbabaie
SIAM Journal on Mathematics of Data Science (SIMODS), 2022

Better Skill-based Job Representations, Assessed via Job Transition Data
Tyler Baldwin, Wyatt Clarke, Maysa Macedo, Rogerio Paula, Subhro Das
IEEE International Conference on BigData, 2022

Learning skills adjacency representations for optimized reskilling recommendations
Saksham Gandhi, Raj Nagesh, Subhro Das
IEEE International Conference on BigData, 2022


2021

On Multisensor Activation Policies for Bernoulli Tracking
Augustin Saucan, Subhro Das, Moe Z. Win
Military Communications Conference (MILCOM), 2021

NEO: NEuro-inspired Optimization - A Fractional Time Series Approac
Sarthak Chatterjee, Subhro Das, Sergio Pequito
Frontiers in Physiology - Inference, Causality and Control in Networks of Dynamical Systems , 2021

Reducing greenhouse gas emissions by optimizing room temperature set-points
Yuan Cai, Jasmina Burek, Subhro Das, Jeremy Gregory, Leslie Norford, Julia Wang, Kevin Kircher
ICML Workshop on Tackling Climate Change with Machine Learning, 2021

IF: Iterative Fractional Optimization
Sarthak Chatterjee, Subhro Das, Sergio Pequito
Proceedings of the 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), 2021

How universities can mind the skills gap: higher education and the future of work
Carlos Lastra-Anadon, Subhro Das, Kush Varshney, Hari Raghavan and Renzhe Yu
Technical Report, Center for the Governance of Change (CGC), 2021

A Research Framework for Understanding Education-Occupation Alignment with NLP Techniques
Renzhe Yu, Subhro Das, Sairam Gurajada, Kush Varshney, Hari Raghavan and Carlos Lastra-Anadon
Proceedings of the ACL Workshop on NLP for Positive Impact, 2021

Fair Selective Classification via Sufficiency
Joshua Lee, Yuheng Bu, Deepta Rajan, Prasanna Sattigeri, Rameswar Panda, Subhro Das, Gregory Wornell
International Conference on Machine Learning (ICML), 2021

Online Optimal Control with Affine Constraints
Yingying Li, Subhro Das, and Na Li
AAAI Conference on Artificial Intelligence (AAAI), 2021

Verifiably Safe Exploration for End-to-End Reinforcement Learning
Nathan Hunt, Nathan Fulton, Sara Magliacane, Nghia Hoang, Subhro Das, Armando Solar-Lezama
ACM International Conference on Hybrid Systems: Computation and Control (HSCC), 2021
** Best Paper Award **


2020

Forecasting Task-Shares and Characterizing Occupational Change across Industry Sectors
Subhro Das, Sebastian Steffen, Prabhat Reddy, Erik Brynjolfsson, Martin Fleming
Harvard CRCS Workshop on AI for Social Good, 2020

Efficient Goal Attainment and Engagement in a Care Manager System Using Unstructured Notes
Sara Rosenthal, Subhro Das, Pei-Yun Hsueh, Ken Barker, Ching-Hua Chen
Journal of the American Medical Informatics Association (JAMIA) Open, 2020

Learning Occupational Task-Shares Dynamics for the Future of Work
Subhro Das, Sebastian Steffen, Wyatt Clarke, Prabhat Reddy, Erik Brynjolfsson, Martin Fleming
Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (AIES), 2020

Learning Interpretable Behavioral Engagement for Care Management
Subhro Das, Chandramouli Maduri, Ching-Hua Chen, Pei-Yun S. Hsueh
Proceedings of the 30th Medical Informatics Europe (MIE) Conference, 2020

Interpretable Subgroup Discovery in Treatment Effect Estimation with Application to Opioid Prescribing Guidelines
Chirag Nagpal, Dennis Wei, Bhanukiran Vinzamuri, Monica Shekhar, Sara E. Berger, Subhro Das, Kush R. Varshney
Proceedings of the ACM Conference on Health, Inference, and Learning, 2020


2019

Learning Patient Engagement in Care Management: Performance vs. Interpretability
Subhro Das, Chandramouli Maduri, Ching-Hua Chen, Pei-Yun S. Hsueh
arXiv preprint, arXiv:1906.08339, 2019

The Future of Work: How New Technologies Are Transforming Tasks
Martin Fleming, Wyatt Clarke, Subhro Das, Phai Phongthiengtham, Prabhat Reddy
MIT-IBM Watson AI Lab , 2019

Formal Verification of End-to-End Learning in Cyber-Physical Systems: Progress and Challenges
Nathan Fulton, Nathan Hunt, Nghia Hoang, Subhro Das
Workshop on Safety and Robustness in Decision Making, NeurIPS, 2019


2018

An Adaptive, Data- Driven Personalized Advisor for Increasing Physical Activity
Zhiguo Li, Subhro Das, James Codella, Tian Hao, Kun Lin, Chandramouli Maduri, and, Ching-Hua Chen
IEEE Journal of Biomedical and Health Informatics, 2018

Learning to Personalize from Practice: A Real World Evidence Approach of Care Plan Personalization based on Differential Patient Behavioral Responses in Care Management Records
Pei-Yun Hsueh, Subhro Das, Chandramouli Maduri, and Karie Kelley
Proceedings of AMIA Annual Symposium, 2018
**Distinguished Paper Award**


2017

A Personalized Pacing System for Real-time Physical Activity Advisor
Henry Chang, Zhiguo Li, Subhro Das, Tian Hao, Chandramouli Maduri, Chohreh Partovian, James Codella, Ching-Hua Chen
Proceedings of IEEE/ACM CHASE, 2017

Making Sense of Patient-Generated Health Data for Interpretable Patient-Centered Care: The Transition from
Pei-Yun Hsueh, Sanjoy Dey, Subhro Das, Thomas Wetter
Studies in Health Technology and Informatics, 2017

Distributed estimation of random fields over multi-agent networks
Subhro Das, Jose M. F. Moura
42nd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017

Consensus+Innovations Distributed Kalman Filter with Optimized Gains
Subhro Das, Jose M. F. Moura
IEEE Transactions on Signal Processing, IEEE, 2017



2016

Distributed Linear Filtering and Prediction of Time-varying Random Fields
Subhro Das
Dissertations. 765, Carnegie Mellon University, 2016



2015

Distributed Kalman filtering with dynamic observations consensus
Subhro Das, Jose M. F. Moura
IEEE Transactions on Signal Processing 63(17), 4458--4473, IEEE, 2015


2013

Distributed state estimation in multi-agent networks
Subhro Das, Jose M. F. Moura
38th IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4246-4250, 2013

Distributed Kalman Filtering
Subhro Das, Jose M. F. Moura
21st European Signal Processing Conference, pp. 1-5, 2013

Distributed linear estimationof dynamic random fileds
Subhro Das, Jose M. F. Moura
51st Annual Allerton Conference on Communication, Control, and Computing, pp. 1120-1125, 2013

Distributed Kalman filtering and network tracking capacity
Subhro Das, Jose M. F. Moura
47th Asilomar Conference on Signals, Systems, and Computers, pp. 629-633, 2013