activity
20102026
most citedGradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks

154 citations · 861 across the 94 of their papers we have counts for

collaborators
Showing 2013Show all

5 papers · 1 filter

cs.IT2013★ 16 cited

Simple Bounds for Noisy Linear Inverse Problems with Exact Side Information

Samet Oymak, Christos Thrampoulidis, Babak Hassibi

This paper considers the linear inverse problem where we wish to estimate a structured signal from its corrupted observations. When the problem is ill-posed, it is natural to m…

cs.IT2013

The Squared-Error of Generalized LASSO: A Precise Analysis

Samet Oymak, Christos Thrampoulidis, Babak Hassibi

We consider the problem of estimating an unknown signal from noisy linear observations . In many practical instances, has a certain structure that…

cs.IT2013★ 9 cited

Sparse Phase Retrieval: Uniqueness Guarantees and Recovery Algorithms

Kishore Jaganathan, Samet Oymak, Babak Hassibi

The problem of signal recovery from its Fourier transform magnitude is of paramount importance in various fields of engineering and has been around for over 100 years. Due to the a…

cs.IT2013★ 18 cited

Sharp MSE Bounds for Proximal Denoising

Samet Oymak, Babak Hassibi

Denoising has to do with estimating a signal from its noisy observations . In this paper, we focus on the "structured denoising problem", where the signal poss…

cs.IT2013★ 21 cited

Sparse Phase Retrieval: Convex Algorithms and Limitations

Kishore Jaganathan, Samet Oymak, Babak Hassibi

We consider the problem of recovering signals from their power spectral density. This is a classical problem referred to in literature as the phase retrieval problem, and is of par…