Search Results - "Soltanolkotabi, Mahdi"

Structured Signal Recovery From Quadratic Measurements: Breaking Sample Complexity Barriers via Nonconvex Optimization by Soltanolkotabi, Mahdi

“…This paper concerns the problem of recovering an unknown but structured signal <inline-formula> <tex-math notation="LaTeX">{x}\in \mathbb {R} ^{n}…”
Get full text

Phase retrieval from coded diffraction patterns by Candès, Emmanuel J., Li, Xiaodong, Soltanolkotabi, Mahdi

“…This paper considers the question of recovering the phase of an object from intensity-only measurements, a problem which naturally appears in X-ray…”
Get full text

Convergence and Sample Complexity of Gradient Methods for the Model-Free Linear-Quadratic Regulator Problem by Mohammadi, Hesameddin, Zare, Armin, Soltanolkotabi, Mahdi, Jovanovic, Mihailo R.

“…Model-free reinforcement learning attempts to find an optimal control action for an unknown dynamical system by directly searching over the parameter space of…”
Get full text

Precise statistical analysis of classification accuracies for adversarial training by Javanmard, Adel, Soltanolkotabi, Mahdi

“…Despite the wide empirical success of modern machine learning algorithms and models in a multitude of applications, they are known to be highly susceptible to…”
Get full text

Generalized Line Spectral Estimation via Convex Optimization by Heckel, Reinhard, Soltanolkotabi, Mahdi

“…Line spectral estimation is the problem of recovering the frequencies and amplitudes of a mixture of a few sinusoids from equispaced samples. However, in a…”
Get full text

Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks by Soltanolkotabi, Mahdi, Javanmard, Adel, Lee, Jason D.

“…In this paper, we study the problem of learning a shallow artificial neural network that best fits a training data set. We study this problem in the…”
Get full text

Toward Moderate Overparameterization: Global Convergence Guarantees for Training Shallow Neural Networks by Oymak, Samet, Soltanolkotabi, Mahdi

“…Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset…”
Get full text

Phase Retrieval via Wirtinger Flow: Theory and Algorithms by Candes, Emmanuel J., Xiaodong Li, Soltanolkotabi, Mahdi

“…We study the problem of recovering the phase from magnitude measurements; specifically, we wish to reconstruct a complex-valued signal x ∈ ℂ n about which we…”
Get full text

Sharp Time-Data Tradeoffs for Linear Inverse Problems by Oymak, Samet, Recht, Benjamin, Soltanolkotabi, Mahdi

“…In this paper, we characterize sharp time-data tradeoffs for optimization problems used for solving linear inverse problems. We focus on the minimization of a…”
Get full text

On the Linear Convergence of Random Search for Discrete-Time LQR by Mohammadi, Hesameddin, Soltanolkotabi, Mahdi, Jovanovic, Mihailo R.

“…Model-free reinforcement learning techniques directly search over the parameter space of controllers. Although this often amounts to solving a nonconvex…”
Get full text

Experimental robustness of Fourier ptychography phase retrieval algorithms by Yeh, Li-Hao, Dong, Jonathan, Zhong, Jingshan, Tian, Lei, Chen, Michael, Tang, Gongguo, Soltanolkotabi, Mahdi, Waller, Laura

“…Fourier ptychography is a new computational microscopy technique that provides gigapixel-scale intensity and phase images with both wide field-of-view and high…”
Get full text

ROBUST SUBSPACE CLUSTERING by Soltanolkotabi, Mahdi, Elhamifar, Ehsan, Candès, Emmanuel J.

“…Subspace clustering refers to the task of finding a multi-subspace representation that best fits a collection of points taken from a high-dimensional space…”
Get full text

Deep Learning Techniques for Inverse Problems in Imaging by Ongie, Gregory, Jalal, Ajil, Metzler, Christopher A., Baraniuk, Richard G., Dimakis, Alexandros G., Willett, Rebecca

“…Recent work in machine learning shows that deep neural networks can be used to solve a wide variety of inverse problems arising in computational imaging. We…”
Get full text

A GEOMETRIC ANALYSIS OF SUBSPACE CLUSTERING WITH OUTLIERS by Soltanolkotabi, Mahdi, Candés, Emmanuel J.

“…This paper considers the problem of clustering a collection of unlabeled data points assumed to lie near a union of lower-dimensional planes. As is common in…”
Get full text

Super-resolution radar by Heckel, Reinhard, Morgenshtern, Veniamin I., Soltanolkotabi, Mahdi

“…In this paper, we study the identification of a time-varying linear system from its response to a known input signal. More specifically, we consider systems…”
Get full text

Isometric sketching of any set via the Restricted Isometry Property by Oymak, Samet, Recht, Benjamin, Soltanolkotabi, Mahdi

“…Abstract In this paper we show that for the purposes of dimensionality reduction certain class of structured random matrices behave similarly to random…”
Get full text

CUDA: Convolution-Based Unlearnable Datasets by Sadasivan, Vinu Sankar, Soltanolkotabi, Mahdi, Feizi, Soheil

“…Large-scale training of modern deep learning models heavily relies on publicly available data on the web. This potentially unauthorized usage of online data…”
Get full text

On The Effectiveness of Active Learning by Uncertainty Sampling in Classification of High-Dimensional Gaussian Mixture Data by Mai, Xiaoyi, Avestimehr, Salman, Ortega, Antonio, Soltanolkotabi, Mahdi

“…Active learning aims to reduce the cost of labeling through selective sampling. Despite reported empirical success over passive learning, many popular active…”
Get full text

A unified approach to sparse signal processing by Marvasti, Farokh, Amini, Arash, Haddadi, Farzan, Soltanolkotabi, Mahdi, Khalaj, Babak Hossein, Aldroubi, Akram, Sanei, Saeid, Chambers, Janathon

“…A unified view of the area of sparse signal processing is presented in tutorial form by bringing together various fields in which the property of sparsity has…”
Get full text

Accelerated Wirtinger Flow for Multiplexed Fourier Ptychographic Microscopy by Bostan, Emrah, Soltanolkotabi, Mahdi, Ren, David, Waller, Laura

“…Fourier ptychographic microscopy enables gigapixel-scale imaging, with both large field-of-view and high resolution. Using a set of low-resolution images that…”
Get full text