A. Gupte

activity

20212026

most citedSGD and Weight Decay Secretly Minimize the Rank of Your Neural Network

1 citations · 1 across the 9 of their papers we have counts for

collaborators

Showing cs.LGShow all

3 papers · 1 filter

cs.LG2024

Sparse Linear Regression and Lattice Problems

Aparna Gupte, Neekon Vafa, Vinod Vaikuntanathan

Sparse linear regression (SLR) is a well-studied problem in statistics where one is given a design matrix $X \in R^{m \times n}$ and a response vector $y = X θ^{*} + w$ for a $k$ -sp…

cs.LG2022★ 1 cited

SGD and Weight Decay Secretly Minimize the Rank of Your Neural Network

Tomer Galanti, Zachary S. Siegel, Aparna Gupte +1

We investigate the inherent bias of Stochastic Gradient Descent (SGD) toward learning low-rank weight matrices during the training of deep neural networks. Our results demonstrate…

cs.LG2021

The Fine-Grained Hardness of Sparse Linear Regression

Aparna Gupte, Vinod Vaikuntanathan

Sparse linear regression is the well-studied inference problem where one is given a design matrix $A \in R^{M \times N}$ and a response vector $\mathbf{b} \in \mat…