24 citations · 62 across the 8 of their papers we have counts for
9 papers
Asymptotics of the Sketched Pseudoinverse
Daniel LeJeune, Pratik Patil, Hamid Javadi +2
We take a random matrix theory approach to random sketching and show an asymptotic first-order equivalence of the regularized sketched pseudoinverse of a positive semidefinite matr…
A Blessing of Dimensionality in Membership Inference through Regularization
Jasper Tan, Daniel LeJeune, Blake Mason +2
Is overparameterization a privacy liability? In this work, we study the effect that the number of parameters has on a classifier's vulnerability to membership inference attacks. We…
Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference
Jasper Tan, Blake Mason, Hamid Javadi +1
A surprising phenomenon in modern machine learning is the ability of a highly overparameterized model to generalize well (small error on the test data) even when it is trained to m…
The Flip Side of the Reweighted Coin: Duality of Adaptive Dropout and Regularization
Daniel LeJeune, Hamid Javadi, Richard G. Baraniuk
Among the most successful methods for sparsifying deep (neural) networks are those that adaptively mask the network weights throughout training. By examining this masking, or dropo…
The Implicit Regularization of Ordinary Least Squares Ensembles
Daniel LeJeune, Hamid Javadi, Richard G. Baraniuk
Ensemble methods that average over a collection of independent predictors that are each limited to a subsampling of both the examples and features of the training data command a si…
Implicit Rugosity Regularization via Data Augmentation
Daniel LeJeune, Randall Balestriero, Hamid Javadi +1
Deep (neural) networks have been applied productively in a wide range of supervised and unsupervised learning tasks. Unlike classical machine learning algorithms, deep networks typ…
False Discovery Rate Control via Debiased Lasso
Adel Javanmard, Hamid Javadi
We consider the problem of variable selection in high-dimensional statistical models where the goal is to report a set of variables, out of many predictors , that…
Porcupine Neural Networks: (Almost) All Local Optima are Global
Soheil Feizi, Hamid Javadi, Jesse Zhang +1
Neural networks have been used prominently in several machine learning and statistics applications. In general, the underlying optimization of neural networks is non-convex which m…
Preconditioning via Diagonal Scaling
Reza Takapoui, Hamid Javadi
Interior point methods solve small to medium sized problems to high accuracy in a reasonable amount of time. However, for larger problems as well as stochastic problems, one needs…