Rishabh Dudeja

About Me

I am a postdoctoral researcher in the Department of Statistics and the School of Engineering and Applied Sciences at Harvard University. 

I am fortunate to work with Prof. Subhabrata Sen and Prof. Yue M. Lu.

My research interests lie in the mathematical foundations of data science, high-dimensional statistics, information theory, signal processing, and applied probability. 

I am particularly interested in understanding phase transitions, universality phenomena, and computational-statistical trade-offs in modern high-dimensional inference problems. 

Previously, I was a Ph.D. student at the Statistics Department at Columbia University, where I was fortunate to be advised by Prof. Arian Maleki and Prof. Daniel Hsu.

You can find more information about me in my CV

rishabhd (at) fas (dot) harvard (dot) edu (for the duration of my postdoc);
rd2714 (at) columbia (dot) edu (permanent).

Department of Statistics, Harvard University
Science Center, Room 602, 1 Oxford Street
Cambridge, MA 02138-2901.





Spectral Universality of Regularized Linear Regression with Nearly Deterministic Sensing Matrices.
Rishabh Dudeja, Subhabrata Sen, Yue M. Lu.
Preprint, 2022.


Statistical-Computational Trade-offs in Tensor PCA and Related Problems via Communication Complexity.
Rishabh Dudeja, Daniel Hsu.
Preprint, 2022.


Universality of Approximate Message Passing with Semi-Random Matrices.
Rishabh Dudeja, Yue M. Lu, Subhabrata Sen.
Preprint, 2022.


Universality of Linearized Message Passing for Phase Retrieval with Structured Sensing Matrices.
Rishabh Dudeja, Milad Bakhshizadeh.
Transactions on Information Theory, 2022 [Journal Link].


Statistical Query Lower Bounds for Tensor PCA.
Rishabh Dudeja, Daniel Hsu.
Journal of Machine Learning Research, 2021 [Journal Link].


Spectral Method for Phase Retrieval: an Expectation Propagation Perspective.
Junjie Ma, Rishabh Dudeja, Ji Xu, Arian Maleki, Xiaodong Wang.
Transactions on Information Theory, 2021 [Journal Link].


Information Theoretic Limits for Phase Retrieval with Subsampled Haar Sensing Matrices.
Rishabh Dudeja, Junjie Ma, Arian Maleki.
Transactions on Information Theory, 2020 [Journal Link].


Analysis of Spectral Methods for Phase Retrieval with Random Orthogonal Matrices. 
Rishabh Dudeja, Milad Bakhshizadeh, Junjie Ma, Arian Maleki.
Transactions on Information Theory, 2020 [Journal Link].


Attribute-efficient learning of monomials over highly-correlated variables.
Alexandr Andoni, Rishabh Dudeja, Daniel Hsu, Kiran Vodrahalli. 
Conference on Algorithmic Learning Theory (ALT),  2019.


Learning single-index models in Gaussian space
Rishabh Dudeja, Daniel Hsu
Conference on Learning Theory (COLT),  2018.




Currently, I am a Teaching Fellow for Mathematics of High-dimensional Information Processing and Learning (AM 254), taught by Prof. Yue M. Lu.

Previously, I served as a TA for the following courses at Columbia:

  • Applied Linear Regression Analysis (B.A./M.A. Level) in Fall 2015.
  • Introduction to Statistics (B.A. Level) in Spring 2016 and Spring 2021.
  • Linear Regression Models (B.A./M.A. Level) in Fall 2016.
  • Applied Categorical Data Analysis (B.A. Level) in Spring 2017 and Spring 2018.
  • Probability and Statistical Inference (M.A. Level) in Fall 2017.
  • Statistical Computing and Introduction to Data Science (B.A./M.A. Level) in  Fall 2018.
  • Multivariate Statistical Inference (B.A./M.A. Level) in Spring 2019.
  • Statistical Inference and Time Series Modelling (B.A./M.A. Level) in  Fall 2019, Spring 2020, and Fall 2020.