Kiran Vodrahalli

{about} {research} {talks} {blog} {archive} {teaching} {notes} {links} {press}




I am a Computer Science Ph.D. student at Columbia University, focusing on theoretical computer science, with particular interest in machine learning, algorithms, and statistics. I am extremely fortunate to be advised by Professor Daniel Hsu and Professor Alex Andoni. I am supported by an NSF Graduate Research Fellowship.


Other Info:

For more details, either check out this website or see my [CV] .

Research Interests

My primary area of research is theoretical computer science: in particular, provably resource-efficient algorithms for fitting statistical models in various settings (“algorithmic statistics”, “foundations of machine learning”, “learning theory”, etc.). Some of my work in this direction has skewed in the direction of giving computationally efficient, low sample complexity algorithms for learning functions with sparse descriptions. I am also interested in algorithms and optimization theory. I have also worked on applications of machine learning in several fields, including neuroscience, natural language understanding, economics, and robotics. Currently, I am particularly focused on applying ideas from machine learning (online learning, learning in games) and bi-level optimization to understand computational and statistical issues associated with the economics of the online firm, as well as associated privacy, ethics, and fairness concerns (see my recent paper The Platform Design Problem).


In Summer 2019 I visited the Simons Institute at Berkeley for the Foundations of Deep Learning program.

I graduated from Princeton with an A.B. Mathematics degree with honors in 2016 and an M.S.E. in Computer Science in 2017, where I was lucky to have Professor Sanjeev Arora and Professor Ken Norman as thesis advisors. I was a member of Sanjeev Arora’s Unsupervised Learning Group, where I studied provable methods for machine learning (also a part of NLP @ Princeton and ML Theory @Princeton), in particular focusing on natural language understanding. I was also a member of Ken Norman’s Computational Memory Lab at the Princeton Neuroscience Institute, where I applied machine learning to fMRI analysis methods.