My research interests include information theory, high-dimensional statistics, signal processing, and machine learning. I am also interested in the application of techniques from these areas to problems in biology. You can find below some papers and slides representative of my recent work.


I co-organize the Cambridge Information Theory Seminar with Varun Jog. Please contact me or Varun if you'd like to give a talk or suggest speakers.


Diffusion-based Generative Models

  • N. Khelifa, R. Turner, R.Venkataramanan, "Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors", accepted to NeurIPS 2026. [PDF]
  • N. Khelifa, R. Turner, R.Venkataramanan, "Quantifying Error Propagation and Model Collapse in Diffusion Models", ICML 2026. [PDF] [Slides]
  • N. Khelifa, R. Turner, R.Venkataramanan, "Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization", accepted to NeurIPS 2026 (Spotlight). [PDF]

High-dimensional Statistics

  • J. Zhou, R. Venkataramanan, H. Zou, "Precise Asymptotics for Dense High-Dimensional Huber Regression under Heteroscedasticity", 2026. [PDF]
  • G. Arpino and R. Venkataramanan, "Inferring Change Points in Regression via Sample Weighting", 2026. [PDF]
  • Y. Zhang, H. C. Ji, R.Venkataramanan, M. Mondelli, "Optimal Estimation in Orthogonally Invariant Generalized Linear Models: Spectral Initialization and Approximate Message Passing", 2026. [PDF] [Slides]
  • G. Arpino, X. Liu, and R. Venkataramanan, "Inferring Change Points in High-Dimensional Regression via Approximate Message Passing", Journal of Machine Learning Research, vol. 26, no. 225, pp. 1-49, 2025. [PDF]
  • Y. Zhang, H. C. Ji, R. Venkataramanan, M. Mondelli, "Spectral Estimators for Structured Generalized Linear Models via Approximate Message Passing", Mathematical Statistics and Learning, vol.8, no.3/4, pp. 193-304, 2025. [PDF]
  • O. Feng, R. Venkataramanan, C. Rush, R. Samworth, "A unifying tutorial on Approximate Message Passing" Foundations and Trends in Machine Learning, vol. 15, no. 4, pp. 335-536, 2022. [PDF]
  • P. Pascual Cobo, K. Hsieh, R. Venkataramanan, "Bayes-Optimal Estimation in Generalized Linear Models via Spatial Coupling", IEEE Transactions on Information Theory, vol. 70, no. 11, pp. 8343-8363, November 2024. [PDF] [Talk at Cambridge Information Theory Seminar]
  • N. Tan, P. Pascual Cobo, J. Scarlett, and R. Venkataramanan, "Approximate Message Passing with Rigorous Guarantees for Pooled Data and Quantitative Group Testing", SIAM Journal on Mathematics of Data Science, vol. 6, no. 4, pp. 1027-1054, 2024. [PDF]
  • G. Arpino, R. Venkataramanan, "Statistical-Computational Tradeoffs in Mixed Sparse Linear Regression", COLT 2023. [PDF]
  • A. Montanari and R. Venkataramanan, "Estimation of Low-Rank Matrices via Approximate Message Passing", Annals of Statistics, vol. 49, no. 1, pp. 321-345, February 2021. [PDF] [Slides from CCIMI seminar, 2018]

Information Theory and Communications

  • G. Reeves, R.Venkataramanan, "Lossy Compression via Sparse Regression Codes: Generalized Construction and Finite-length Bounds", IEEE Information Theory Workshop, 2026. [PDF]
  • X. Liu, P. Pascual Cobo, and R. Venkataramanan, "Many-User Multiple Access with Random User Activity: Achievability Bounds and Efficient Schemes", IEEE Transactions on Information Theory, vol. 72, no. 1, pp. 383-414, January 2026. [PDF]
  • X. Liu, K. Hsieh, and R. Venkataramanan, "Coded many-user multiple access via AMP", ISIT 2024. [PDF]
  • R. Venkataramanan, S. Tatikonda and A. Barron, "Sparse Regression Codes", Foundations and Trends in Communications and Information Theory, vol. 15, no. 1-2, pp. 1-195, 2019. [PDF]
  • K. Hsieh, C. Rush, and R. Venkataramanan, "Near-optimal coding for many-user multiple access channels", IEEE Journal on Selected Areas in Information Theory, vol. 3, no. 1, pp. 21-36, March 2022. [PDF] [Slides from Oberwolfach workshop talk]
  • C. Rush, K. Hsieh, and R. Venkataramanan, "Capacity-achieving spatially coupled sparse superposition codes with AMP decoding", IEEE Transactions on Information Theory, vol. 67, no. 7, pp. 4446 - 4484, July 2021. [PDF]