activity
20152022
most citedThe LASSO with Non-linear Measurements is Equivalent to One With Linear Measurements

90 citations · 152 across the 8 of their papers we have counts for

collaborators

12 papers

cs.LG202228 cited

AutoBalance: Optimized Loss Functions for Imbalanced Data

Mingchen Li, Xuechen Zhang, Christos Thrampoulidis +2

Imbalanced datasets are commonplace in modern machine learning problems. The presence of under-represented classes or groups with sensitive attributes results in concerns about gen…

cs.LG2021

Label-Imbalanced and Group-Sensitive Classification under Overparameterization

Ganesh Ramachandra Kini, Orestis Paraskevas, Samet Oymak +1

The goal in label-imbalanced and group-sensitive classification is to optimize relevant metrics such as balanced error and equal opportunity. Classical methods, such as weighted cr…

cs.LG20204 cited

Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks

Xiangyu Chang, Yingcong Li, Samet Oymak +1

Deep networks are typically trained with many more parameters than the size of the training dataset. Recent empirical evidence indicates that the practice of overparameterization n…

cs.LG202013 cited

Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View

Christos Thrampoulidis, Samet Oymak, Mahdi Soltanolkotabi

Contemporary machine learning applications often involve classification tasks with many classes. Despite their extensive use, a precise understanding of the statistical properties…

cs.LG20205 cited

Exploring Weight Importance and Hessian Bias in Model Pruning

Mingchen Li, Yahya Sattar, Christos Thrampoulidis +1

Model pruning is an essential procedure for building compact and computationally-efficient machine learning models. A key feature of a good pruning algorithm is that it accurately…

cs.IT2018

The Generalized Lasso for Sub-gaussian Measurements with Dithered Quantization

Christos Thrampoulidis, Ankit Singh Rawat

In the problem of structured signal recovery from high-dimensional linear observations, it is commonly assumed that full-precision measurements are available. Under this assumption…