About me

I am a fourth year Ph.D student of Electrical Engineering at Caltech where I am grateful to be advised by Babak Hassibi. I am interested in the theory of deep learning, random matrix theory, control theory, and signal processing.

I received my M.Sc degree in Electrical Engineering from California Institute of Technology in 2024 and my B.Sc in Electrical Engineering and Mathematics from Sharif University of Technology in 2022.

Publications

• One-Bit Quantization for Random Features Models
  Danil Akhtiamov*, Reza Ghane*, and Babak Hassibi
  Under review
  [Arxiv]
• A Precise Performance Analysis of the Randomized Singular Value Decomposition
  Danil Akhtiamov*, Reza Ghane*, and Babak Hassibi
  2025 Allerton Conference on Communication, Control, and Computing
  [Arxiv]
• Beyond Quadratic Costs: A Bregman Divergence Approach to H∞ Control
  Joudi Hajar, Reza Ghane, and Babak Hassibi
  64th IEEE Conference on Decision and Control (CDC 2025)
  [Arxiv]
• Beyond Quadratic Costs in LQR: Bregman Divergence Control
  Babak Hassibi, Joudi Hajar, and Reza Ghane
  64th IEEE Conference on Decision and Control (CDC 2025)
  [Arxiv]
• Robust Mean Estimation With Auxiliary Samples
  Barron Han*, Danil Akhtiamov*, Reza Ghane*, and Babak Hassibi
  [Arxiv]
• Gaussian Universality for Diffusion Models
  Reza Ghane*, Anthony Bao*, Danil Akhtiamov*, and Babak Hassibi
  IEEE Signal Processing Letters [Arxiv]
• Universality in Transfer Learning for Linear Models
  Reza Ghane*, Danil Akhtiamov*, and Babak Hassibi
  Neural Information Processing Systems (NeurIPS) 2024
  [Arxiv]
• One-Bit Quantization and Sparsification for Multiclass Linear Classification via Regularized Regression
  Reza Ghane*, Danil Akhtiamov*, and Babak Hassibi
  IEEE Transactions on Signal Processing (2025)
  [IEEE], [Arxiv]
• A Novel Gaussian Min-Max Theorem and its Applications
  Danil Akhtiamov*, David Bosch*, Reza Ghane*, K Nithin Varma, and Babak Hassibi
  IEEE Transactions on Information Theory (2025).
  [IEEE], [Arxiv]
• Regularized Linear Regression for Binary Classification
  Danil Akhtiamov*, Reza Ghane*, and Babak Hassibi
  2024 IEEE International Symposium on Information Theory (ISIT) (pp. 202-207)
  [ISIT], [Arxiv]