1 citations · 2 across the 13 of their papers we have counts for
13 papers
Precise Performance of Linear Denoisers in the Proportional Regime
Reza Ghane, Danil Akhtiamov, Babak Hassibi
In the present paper we study the performance of linear denoisers for noisy data of the form , where is the desired data with…
Dual Space Preconditioning for Gradient Descent in the Overparameterized Regime
Reza Ghane, Danil Akhtiamov, Babak Hassibi
In this work, we study the convergence properties of the Dual Space Preconditioned Gradient Descent, encompassing optimizers such as Normalized Gradient Descent and Gradient Clippi…
Implicit Bias and Convergence of Matrix Stochastic Mirror Descent
Danil Akhtiamov, Reza Ghane, Omead Pooladzandi +1
We investigate Stochastic Mirror Descent (SMD) with matrix parameters and vector-valued predictions, a framework relevant to multi-class classification and matrix completion proble…
One-Bit Quantization for Random Features Models
Danil Akhtiamov, Reza Ghane, Babak Hassibi
Recent advances in neural networks have led to significant computational and memory demands, spurring interest in one-bit weight compression to enable efficient inference on resour…
A Precise Performance Analysis of the Randomized Singular Value Decomposition
Danil Akhtiamov, Reza Ghane, Babak Hassibi
The Randomized Singular Value Decomposition (RSVD) is a widely used algorithm for efficiently computing low-rank approximations of large matrices, without the need to construct a f…
Beyond Quadratic Costs: A Bregman Divergence Approach to H Control
Joudi Hajar, Reza Ghane, Babak Hassibi
In the past couple of decades, non-quadratic convex penalties have reshaped signal processing and machine learning; in robust control, however, general convex costs break the Ricca…
Beyond Quadratic Costs in LQR: Bregman Divergence Control
Babak Hassibi, Joudi Hajar, Reza Ghane
In the past couple of decades, the use of ``non-quadratic" convex cost functions has revolutionized signal processing, machine learning, and statistics, allowing one to customize s…
Robust Mean Estimation With Auxiliary Samples
Barron Han, Danil Akhtiamov, Reza Ghane +1
In data-driven learning and inference tasks, the high cost of acquiring samples from the target distribution often limits performance. A common strategy to mitigate this challenge…
Gaussian Universality for Diffusion Models
Reza Ghane, Anthony Bao, Danil Akhtiamov +1
We investigate Gaussian Universality for data distributions generated via diffusion models. By Gaussian Universality we mean that the test error of a generalized linear model $f(\m…
Universality in Transfer Learning for Linear Models
Reza Ghane, Danil Akhtiamov, Babak Hassibi
We study the problem of transfer learning and fine-tuning in linear models for both regression and binary classification. In particular, we consider the use of stochastic gradient…
One-Bit Quantization and Sparsification for Multiclass Linear Classification with Strong Regularization
Reza Ghane, Danil Akhtiamov, Babak Hassibi
We study the use of linear regression for multiclass classification in the over-parametrized regime where some of the training data is mislabeled. In such scenarios it is necessary…
A Novel Gaussian Min-Max Theorem and its Applications
Danil Akhtiamov, David Bosch, Reza Ghane +2
A celebrated result by Gordon allows one to compare the min-max behavior of two Gaussian processes if certain inequality conditions are met. The consequences of this result include…
Regularized Linear Regression for Binary Classification
Danil Akhtiamov, Reza Ghane, Babak Hassibi
Regularized linear regression is a promising approach for binary classification problems in which the training set has noisy labels since the regularization term can help to avoid…