4 citations · 17 across the 25 of their papers we have counts for
7 papers · 1 filter
Differentially Private High-dimensional Variable Selection via Integer Programming
Petros Prastakos, Kayhan Behdin, Rahul Mazumder
Sparse variable selection improves interpretability and generalization in high-dimensional learning by selecting a small subset of informative features. Recent advances in Mixed In…
HASSLE-free: A unified Framework for Sparse plus Low-Rank Matrix Decomposition for LLMs
Mehdi Makni, Kayhan Behdin, Zheng Xu +2
The impressive capabilities of large foundation models come at a cost of substantial computing resources to serve them. Compressing these pre-trained models is of practical interes…
QuantEase: Optimization-based Quantization for Language Models
Kayhan Behdin, Ayan Acharya, Aman Gupta +4
With the rising popularity of Large Language Models (LLMs), there has been an increasing interest in compression techniques that enable their efficient deployment. This study focus…
On Statistical Properties of Sharpness-Aware Minimization: Provable Guarantees
Kayhan Behdin, Rahul Mazumder
Sharpness-Aware Minimization (SAM) is a recent optimization framework aiming to improve the deep neural network generalization, through obtaining flatter (i.e. less sharp) solution…
mSAM: Micro-Batch-Averaged Sharpness-Aware Minimization
Kayhan Behdin, Qingquan Song, Aman Gupta +7
Modern deep learning models are over-parameterized, where different optima can result in widely varying generalization performance. The Sharpness-Aware Minimization (SAM) technique…
Sparse NMF with Archetypal Regularization: Computational and Robustness Properties
Kayhan Behdin, Rahul Mazumder
We consider the problem of sparse nonnegative matrix factorization (NMF) using archetypal regularization. The goal is to represent a collection of data points as nonnegative linear…
Recovering Quantized Data with Missing Information Using Bilinear Factorization and Augmented Lagrangian Method
Ashkan Esmaeili, Kayhan Behdin, Sina Al-E-Mohammad +1
In this paper, we propose a novel approach in order to recover a quantized matrix with missing information. We propose a regularized convex cost function composed of a log-likeliho…