Saminul Haque

I am fourth-year Computer Science PhD student at Stanford University, fortunate to be advised by John Duchi and Tatsunori Hashimoto. I am interested in optimal and efficient algorithms in differentially private as well as in robustness.

Email / Google Scholar / CV

Publications

• A fast and slightly robust covariance estimator
  with John Duchi and Rohith Kuditipudi.
  Under review at COLT, 2025.


• Near Exact Privacy Amplification for Matrix Mechanisms
  with Christopher A. Choquette-Choo, Arun Ganesh, Thomas Steinke and Abhradeep Thakurta.
  ICLR, 2025.


• An information-theoretic lower bound in time-uniform estimation
  with John Duchi.
  COLT, 2024.


• Universally Instance-Optimal Mechanisms for Private Statistical Estimation
  with Hilal Asi, John C. Duchi, Zewei Li and Feng Ruan.
  COLT, 2024.


• A Fast Algorithm for Adaptive Private Mean Estimation
  with John Duchi and Rohith Kuditipudi.
  COLT, 2023. Won the Mark Fulk best student paper award.


• Undersampling is a Minimax Optimal Robustness Intervention in Nonparametric Classification
  with Niladri S. Chatterji and Tatsunori Hashimoto.
  TMLR, 2023.


• Is Importance Weighting Incompatible with Interpolating Classifiers?
  with Ke Alexander Wang, Niladri S. Chatterji and Tatsunori Hashimoto.
  ICLR, 2022.


• Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks
  with Qiyang Li, Cem Anil, James R Lucas, Roger B Grosse and Jörn-Henrik Jacobsen. NeurIPS, 2019.


• A comparison of two classifications of solvable Lie algebras
  with Nicholas Bryenton, Cameron Davies, Andrew Douglas, et al.
  Journal of Mathematical Physics 59, no. 12, 2018.