I graduated from Stanford University with a Statistics phd after defending this thesis. I was advised by Professor Iain Johnstone. My dissertation was on predictive density estimation where we established some new minimax decision theoretic phenomena. During my phd, I also collaborated on emerging single-cell virology applications. After graduation, I worked on emprical Bayes theory and methods and have developed efficient shrinkage methods for big-data estimation problems. Along with these research areas, currently I am also interested in the development and theoretical analysis of shrinkage methods for large-scale hierarchical modeling. These methods are inspired by contemporary research problems in pricing strategy and digital marketing that involve large-scale non-linear mixed-effects modeling. Below is a list of the different topics that I’m currently working.

Statistics Theory and Methods

• Predictive Inference
  • Predictive Density Estimation
  • Impact of Loss functions on optimality of predictors
• High-dimensional Decision Theory
  • Shrinkage and Empirical Bayes
  • Minimax optimality
    
  • Sparse Estimation and Penalized Regression methods

Applications and Statistical Methods

• Single Cell Virology
  • Inference under heterogeneity; Clustering
  • Two sample Testing
• Pricing Strategies and Digital Marketing
  • Mixed-effects models and joint modeling
  • Bayesian Shrinkage in Hierarchical models
  • Pricing of (a) Durable products (b) Digital goods.
    
• Inventory Management
  • Quantile and Asymmetric losses