Aditya Makkar

Aditya Makkar

Graduate student

Columbia University

I am a graduate student at Columbia University interested in theoretical machine learning. I am affiliated with the Electrical Engineering Department and the Data Science Institute and am part of a thriving machine learning community here at Columbia. I am advised by Prof. John Paisley.

Previously, I was at Goldman Sachs working with Dr. Howard Karloff on machine learning applications for surveillance models. I received my Bachelors degree from Indian Institute of Technology (IIT) Delhi.

If you’d like to chat, feel free to write me at a ‘dot’ makkar ‘at’ columbia ‘dot’ edu.


My research interests include statistics (especially nonparametric statistics), probability theory and analysis, and their applications in machine learning.

A recent focus of mine has been Reproducing Kernel Hilbert Spaces in probability and statistics, and approximate Bayesian inference methods like variational inference and Monte Carlo.

Current Projects

  1. Bayesian nonparametric ensemble: This is a follow-up on the work of Liu, Paisley, Kioumourtzoglou and Coull - Accurate uncertainty estimation and decomposition in ensemble learning (2019).
  2. Deep correlated topic models: This is an application of the work of Zhang and Paisley - Random Function Priors for Correlation Modeling (2019).

Professional Activities

Reviewer for ICML 2020, AAAI 2021