Mahdi Soltanolkotabi

research

∙ 09/12/2023

Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models

Inverse problems arise in a multitude of applications, where the goal is...

0 Zalan Fabian, et al. ∙

research

∙ 07/25/2023

mL-BFGS: A Momentum-based L-BFGS for Distributed Large-Scale Neural Network Optimization

Quasi-Newton methods still face significant challenges in training large...

0 Yue Niu, et al. ∙

research

∙ 07/24/2023

Learning Provably Robust Estimators for Inverse Problems via Jittering

Deep neural networks provide excellent performance for inverse problems ...

0 Anselm Krainovic, et al. ∙

research

∙ 07/02/2023

Don't Memorize; Mimic The Past: Federated Class Incremental Learning Without Episodic Memory

Deep learning models are prone to forgetting information learned in the ...

0 Sara Babakniya, et al. ∙

research

∙ 06/06/2023

On the Role of Attention in Prompt-tuning

Prompt-tuning is an emerging strategy to adapt large language models (LL...

0 Samet Oymak, et al. ∙

research

∙ 03/25/2023

DiracDiffusion: Denoising and Incremental Reconstruction with Assured Data-Consistency

Diffusion models have established new state of the art in a multitude of...

0 Zalan Fabian, et al. ∙

research

∙ 03/24/2023

Implicit Balancing and Regularization: Generalization and Convergence Guarantees for Overparameterized Asymmetric Matrix Sensing

Recently, there has been significant progress in understanding the conve...

0 Mahdi Soltanolkotabi, et al. ∙

research

∙ 03/07/2023

CUDA: Convolution-based Unlearnable Datasets

Large-scale training of modern deep learning models heavily relies on pu...

0 Vinu Sankar Sadasivan, et al. ∙

research

∙ 12/10/2022

SMILE: Scaling Mixture-of-Experts with Efficient Bi-level Routing

The mixture of Expert (MoE) parallelism is a recent advancement that sca...

12 Chaoyang He, et al. ∙

research

∙ 09/18/2022

The Geometry of Self-supervised Learning Models and its Impact on Transfer Learning

Self-supervised learning (SSL) has emerged as a desirable paradigm in co...

0 Romain Cosentino, et al. ∙

research

∙ 06/30/2022

Neural Networks can Learn Representations with Gradient Descent

Significant theoretical work has established that in specific regimes, n...

0 Alex Damian, et al. ∙

research

∙ 05/13/2022

Toward a Geometrical Understanding of Self-supervised Contrastive Learning

Self-supervised learning (SSL) is currently one of the premier technique...

0 Romain Cosentino, et al. ∙

research

∙ 03/31/2022

Learning from many trajectories

We initiate a study of supervised learning from many independent sequenc...

0 Stephen Tu, et al. ∙

research

∙ 03/15/2022

HUMUS-Net: Hybrid unrolled multi-scale network architecture for accelerated MRI reconstruction

In accelerated MRI reconstruction, the anatomy of a patient is recovered...

0 Zalan Fabian, et al. ∙

research

∙ 11/22/2021

FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks

Federated Learning (FL) is a distributed learning paradigm that can lear...

2 Chaoyang He, et al. ∙

research

∙ 10/06/2021

SSFL: Tackling Label Deficiency in Federated Learning via Personalized Self-Supervision

Federated Learning (FL) is transforming the ML training ecosystem from a...

6 Chaoyang He, et al. ∙

research

∙ 09/23/2021

Outlier-Robust Sparse Estimation via Non-Convex Optimization

We explore the connection between outlier-robust high-dimensional statis...

1 Yu Cheng, et al. ∙

research

∙ 06/28/2021

Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction

Recently there has been significant theoretical progress on understandin...

0 Dominik Stöger, et al. ∙

research

∙ 06/28/2021

Data augmentation for deep learning based accelerated MRI reconstruction with limited data

Deep neural networks have emerged as very successful tools for image res...

72 Zalan Fabian, et al. ∙

research

∙ 04/29/2021

Generalization Guarantees for Neural Architecture Search with Train-Validation Split

Neural Architecture Search (NAS) is a popular method for automatically d...

0 Samet Oymak, et al. ∙

research

∙ 04/12/2021

Understanding Overparameterization in Generative Adversarial Networks

A broad class of unsupervised deep learning methods such as Generative A...

0 Yogesh Balaji, et al. ∙

research

∙ 02/05/2021

PipeTransformer: Automated Elastic Pipelining for Distributed Training of Transformers

The size of Transformer models is growing at an unprecedented pace. It h...

29 Chaoyang He, et al. ∙

research

∙ 11/16/2020

Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View

Contemporary machine learning applications often involve classification ...

0 Christos Thrampoulidis, et al. ∙

research

∙ 10/21/2020

Precise Statistical Analysis of Classification Accuracies for Adversarial Training

Despite the wide empirical success of modern machine learning algorithms...

0 Adel Javanmard, et al. ∙

research

∙ 06/16/2020

Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks

Transfer learning has emerged as a powerful technique for improving the ...

0 Seyed Mohammadreza Mousavi Kalan, et al. ∙

research

∙ 05/26/2020

Approximation Schemes for ReLU Regression

We consider the fundamental problem of ReLU regression, where the goal i...

0 Ilias Diakonikolas, et al. ∙

research

∙ 05/07/2020

Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximation

Un-trained convolutional neural networks have emerged as highly successf...

0 Reinhard Heckel, et al. ∙

research

∙ 05/04/2020

High-Dimensional Robust Mean Estimation via Gradient Descent

We study the problem of high-dimensional robust mean estimation in the p...

0 Yu Cheng, et al. ∙

research

∙ 02/26/2020

3D Phase Retrieval at Nano-Scale via Accelerated Wirtinger Flow

Imaging 3D nano-structures at very high resolution is crucial in a varie...

0 Zalan Fabian, et al. ∙

research

∙ 02/24/2020

Precise Tradeoffs in Adversarial Training for Linear Regression

Despite breakthrough performance, modern learning models are known to be...

0 Adel Javanmard, et al. ∙

research

∙ 12/26/2019

Convergence and sample complexity of gradient methods for the model-free linear quadratic regulator problem

Model-free reinforcement learning attempts to find an optimal control ac...

0 Hesameddin Mohammadi, et al. ∙

research

∙ 10/31/2019

Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators

Convolutional Neural Networks (CNNs) have emerged as highly successful t...

0 Reinhard Heckel, et al. ∙

research

∙ 06/12/2019

Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian

Modern neural network architectures often generalize well despite contai...

0 Samet Oymak, et al. ∙

research

∙ 03/27/2019

Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks

Modern neural networks are typically trained in an over-parameterized re...

0 Mingchen Li, et al. ∙

research

∙ 02/12/2019

Towards moderate overparameterization: global convergence guarantees for training shallow neural networks

Many modern neural network architectures are trained in an overparameter...

0 Samet Oymak, et al. ∙

research

∙ 01/19/2019

Fitting ReLUs via SGD and Quantized SGD

In this paper we focus on the problem of finding the optimal weights of ...

0 Seyed Mohammadreza Mousavi Kalan, et al. ∙

research

∙ 12/25/2018

Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?

Many modern learning tasks involve fitting nonlinear models to data whic...

0 Samet Oymak, et al. ∙

research

∙ 05/24/2018

Polynomially Coded Regression: Optimal Straggler Mitigation via Data Encoding

We consider the problem of training a least-squares regression model on ...

0 Songze Li, et al. ∙

research

∙ 05/16/2018

End-to-end 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...

0 Samet Oymak, et al. ∙

research

∙ 03/31/2018

Fundamental Resource Trade-offs for Encoded Distributed Optimization

Dealing with the shear size and complexity of today's massive data sets ...

0 A. Salman Avestimehr, et al. ∙

research

∙ 10/27/2017

Near-Optimal Straggler Mitigation for Distributed Gradient Methods

Modern learning algorithms use gradient descent updates to train inferen...

0 Songze Li, et al. ∙

research

∙ 07/16/2017

Theoretical insights into the optimization landscape of over-parameterized shallow neural networks

In this paper we study the problem of learning a shallow artificial neur...

0 Mahdi Soltanolkotabi, et al. ∙

research

∙ 05/10/2017

Learning ReLUs via Gradient Descent

In this paper we study the problem of learning Rectified Linear Units (R...

0 Mahdi Soltanolkotabi, et al. ∙

research

∙ 02/20/2017

Structured signal recovery from quadratic measurements: Breaking sample complexity barriers via nonconvex optimization

This paper concerns the problem of recovering an unknown but structured ...

0 Mahdi Soltanolkotabi, et al. ∙

research

∙ 10/23/2016

Fast and Reliable Parameter Estimation from Nonlinear Observations

In this paper we study the problem of recovering a structured but unknow...

0 Samet Oymak, et al. ∙

research

∙ 11/10/2015

Experimental robustness of Fourier Ptychography phase retrieval algorithms

Fourier ptychography is a new computational microscopy technique that pr...

0 Li-Hao Yeh, et al. ∙

research

∙ 06/11/2015

Isometric sketching of any set via the Restricted Isometry Property

In this paper we show that for the purposes of dimensionality reduction ...

0 Samet Oymak, et al. ∙

research

∙ 12/23/2014

Approximate Subspace-Sparse Recovery with Corrupted Data via Constrained ℓ_1-Minimization

High-dimensional data often lie in low-dimensional subspaces correspondi...

0 Ehsan Elhamifar, et al. ∙

research

∙ 01/11/2013

Robust subspace clustering

Subspace clustering refers to the task of finding a multi-subspace repre...

0 Mahdi Soltanolkotabi, et al. ∙

research

∙ 11/05/2012

Discussion: Latent variable graphical model selection via convex optimization

Discussion of "Latent variable graphical model selection via convex opti...

0 Emmanuel J. Candès, et al. ∙

Mahdi Soltanolkotabi

Featured Co-authors