Gauri Jagatap

Gauri Jagatap
New York University | NYU · Department of Electrical and Computer Engineering

Doctor of Philosophy

About

18
Publications
540
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
124
Citations

Publications

Publications (18)
Article
Full-text available
In this paper we propose a new family of algorithms, ATENT, for training adversarially robust deep neural networks. We formulate a new loss function that is equipped with an additional entropic regularization. Our loss function considers the contribution of adversarial samples that are drawn from a specially designed distribution in the data space...
Preprint
Full-text available
Vision transformers rely on a patch token based self attention mechanism, in contrast to convolutional networks. We investigate fundamental differences between these two families of models, by designing a block sparsity based adversarial token attack. We probe and analyze transformer as well as convolutional models with token attacks of varying pat...
Preprint
Full-text available
Deep generative models have emerged as a powerful class of priors for signals in various inverse problems such as compressed sensing, phase retrieval and super-resolution. Here, we assume an unknown signal to lie in the range of some pre-trained generative model. A popular approach for signal recovery is via gradient descent in the low-dimensional...
Preprint
Full-text available
In this paper we propose a new family of algorithms for training adversarially robust deep neural networks. We formulate a new loss function that uses an entropic regularization. Our loss function considers the contribution of adversarial samples which are drawn from a specially designed distribution that assigns high probability to points with hig...
Article
We study the problem of recovering structured data from Fourier ptychography measurements. Fourier ptychography is an image acquisition scheme that uses an array of images to produce high-resolution images in microscopy as well as long-distance imaging, to mitigate the effects of diffraction blurring. The number of measurements is typically much la...
Preprint
Full-text available
Deep neural networks as image priors have been recently introduced for problems such as denoising, super-resolution and inpainting with promising performance gains over hand-crafted image priors such as sparsity and low-rank. Unlike learned generative priors they do not require any training over large datasets. However, few theoretical guarantees e...
Article
We consider the problem of recovering a signal x* ∈ R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</sup> , from magnitude-only measurements, y <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i</sub> = |〈a <sub xmlns:mml="http://www.w3.org/1998/Math/Ma...
Preprint
Full-text available
We propose and analyze a new family of algorithms for training neural networks with ReLU activations. Our algorithms are based on the technique of alternating minimization: estimating the activation patterns of each ReLU for all given samples, interleaved with weight updates via a least-squares step. We consider three different cases of this model:...
Conference Paper
We consider the problem of recovering a signal x in R^n, from magnitude-only measurements, y_i = |a_i^T x| for i={1,2...m}. Also known as the phase retrieval problem, it is a fundamental challenge in nano-, bio- and astronomical imaging systems, astronomical imaging, and speech processing. The problem is ill-posed, and therefore additional assumpti...
Article
Full-text available
We consider the problem of recovering a signal $\mathbf{x}^* \in \mathbf{R}^n$, from magnitude-only measurements, $y_i = |\left\langle\mathbf{a}_i,\mathbf{x}^*\right\rangle|$ for $i=\{1,2,\ldots,m\}$. This is a stylized version of the classical phase retrieval problem, and is a fundamental challenge in bio-imaging systems, astronomical imaging, and...

Network

Cited By