I’m a 2nd year EECS PhD student at MIT advised by Tamara Broderick and Caroline Uhler. I work on scalable Bayesian and causal inference. I am also leading the predictive analytics team at ArbiLex, which enables lawyers and litigation funders to make decisions more effectively through probabilistic and causal modeling.
- Minimal I-MAP MCMC for Scalable Structure Discovery in Causal DAG Models.
Raj Agrawal, Tamara Broderick, Caroline Uhler.
- Data-dependent compression of random features for large-scale kernel approximation.
Raj Agrawal, Trevor Campbell, Jonathan Huggins, Tamara Broderick.
- ABCD-Strategy: Budgeted Experimental Design for Targeted Causal Structure Discovery.
Raj Agrawal, Chandler Squires, Karren Yang, Karthik Shanmugam, Caroline Uhler.
- The Kernel Interaction Trick: Fast Bayesian Discovery of Multi-Way Interactions in High Dimensions.
Raj Agrawal, Jonathan Huggins, Brian Trippe, Tamara Broderick.
- LR-GLM: High-Dimensional Bayesian Inference Using Low-Rank Data Approximations.
Brian Trippe, Jonathan Huggins, Raj Agrawal, Tamara Broderick.
- Covariance Matrix Estimation under Total Positivity for Portfolio Selection.
Raj Agrawal*, Uma Roy*, Caroline Uhler*.
Submitted to the Journal of Financial Econometrics.
- Improving Prediction for Moderate Dimensional Linear Regression by a Data-Driven Choice of Loss Function.
Raj Agrawal*, Noureddine El Karoui*.