
Generalization Guarantees for Neural Architecture Search with TrainValidation Split
Neural Architecture Search (NAS) is a popular method for automatically d...
read it

Understanding Overparameterization in Generative Adversarial Networks
A broad class of unsupervised deep learning methods such as Generative A...
read it

PipeTransformer: Automated Elastic Pipelining for Distributed Training of Transformers
The size of Transformer models is growing at an unprecedented pace. It h...
read it

Theoretical Insights Into Multiclass Classification: A Highdimensional Asymptotic View
Contemporary machine learning applications often involve classification ...
read it

Precise Statistical Analysis of Classification Accuracies for Adversarial Training
Despite the wide empirical success of modern machine learning algorithms...
read it

Minimax Lower Bounds for Transfer Learning with Linear and Onehidden Layer Neural Networks
Transfer learning has emerged as a powerful technique for improving the ...
read it

Approximation Schemes for ReLU Regression
We consider the fundamental problem of ReLU regression, where the goal i...
read it

Compressive sensing with untrained neural networks: Gradient descent finds the smoothest approximation
Untrained convolutional neural networks have emerged as highly successf...
read it

HighDimensional Robust Mean Estimation via Gradient Descent
We study the problem of highdimensional robust mean estimation in the p...
read it

3D Phase Retrieval at NanoScale via Accelerated Wirtinger Flow
Imaging 3D nanostructures at very high resolution is crucial in a varie...
read it

Precise Tradeoffs in Adversarial Training for Linear Regression
Despite breakthrough performance, modern learning models are known to be...
read it

Convergence and sample complexity of gradient methods for the modelfree linear quadratic regulator problem
Modelfree reinforcement learning attempts to find an optimal control ac...
read it

Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators
Convolutional Neural Networks (CNNs) have emerged as highly successful t...
read it

Generalization Guarantees for Neural Networks via Harnessing the Lowrank Structure of the Jacobian
Modern neural network architectures often generalize well despite contai...
read it

Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks
Modern neural networks are typically trained in an overparameterized re...
read it

Towards moderate overparameterization: global convergence guarantees for training shallow neural networks
Many modern neural network architectures are trained in an overparameter...
read it

Fitting ReLUs via SGD and Quantized SGD
In this paper we focus on the problem of finding the optimal weights of ...
read it

Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?
Many modern learning tasks involve fitting nonlinear models to data whic...
read it

Polynomially Coded Regression: Optimal Straggler Mitigation via Data Encoding
We consider the problem of training a leastsquares regression model on ...
read it

Endtoend Learning of a Convolutional Neural Network via Deep Tensor Decomposition
In this paper we study the problem of learning the weights of a deep con...
read it

Fundamental Resource Tradeoffs for Encoded Distributed Optimization
Dealing with the shear size and complexity of today's massive data sets ...
read it

NearOptimal Straggler Mitigation for Distributed Gradient Methods
Modern learning algorithms use gradient descent updates to train inferen...
read it

Theoretical insights into the optimization landscape of overparameterized shallow neural networks
In this paper we study the problem of learning a shallow artificial neur...
read it

Learning ReLUs via Gradient Descent
In this paper we study the problem of learning Rectified Linear Units (R...
read it

Structured signal recovery from quadratic measurements: Breaking sample complexity barriers via nonconvex optimization
This paper concerns the problem of recovering an unknown but structured ...
read it

Fast and Reliable Parameter Estimation from Nonlinear Observations
In this paper we study the problem of recovering a structured but unknow...
read it

Experimental robustness of Fourier Ptychography phase retrieval algorithms
Fourier ptychography is a new computational microscopy technique that pr...
read it

Isometric sketching of any set via the Restricted Isometry Property
In this paper we show that for the purposes of dimensionality reduction ...
read it

Approximate SubspaceSparse Recovery with Corrupted Data via Constrained ℓ_1Minimization
Highdimensional data often lie in lowdimensional subspaces correspondi...
read it

Robust subspace clustering
Subspace clustering refers to the task of finding a multisubspace repre...
read it

Discussion: Latent variable graphical model selection via convex optimization
Discussion of "Latent variable graphical model selection via convex opti...
read it

A geometric analysis of subspace clustering with outliers
This paper considers the problem of clustering a collection of unlabeled...
read it
Mahdi Soltanolkotabi
is this you? claim profile
Assistant Professor at University of Southern California since 2015, Postdoctoral Researcher at UC Berkeley 20142015, Instructor at Stanford University 2011, Phd in Electrical Engineering at Stanford University 20092014.