Mahdi Soltanolkotabi

Orcid: 0000-0003-2101-6418

Affiliations:
  • University of Southern California, USA


According to our database1, Mahdi Soltanolkotabi authored at least 89 papers between 2008 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Learning from many trajectories.
J. Mach. Learn. Res., 2024

MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models.
CoRR, 2024

Theoretical Insights into Overparameterized Models in Multi-Task and Replay-Based Continual Learning.
CoRR, 2024

Serpent: Scalable and Efficient Image Restoration via Multi-scale Structured State Space Models.
CoRR, 2024

DiracDiffusion: Denoising and Incremental Reconstruction with Assured Data-Consistency.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023
mL-BFGS: A Momentum-based L-BFGS for Distributed Large-scale Neural Network Optimization.
Trans. Mach. Learn. Res., 2023

Gradient Descent Provably Solves Nonlinear Tomographic Reconstruction.
CoRR, 2023

Learning A Disentangling Representation For PU Learning.
CoRR, 2023

Don't Memorize; Mimic The Past: Federated Class Incremental Learning Without Episodic Memory.
CoRR, 2023

Learning Provably Robust Estimators for Inverse Problems via Jittering.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

On the Role of Attention in Prompt-tuning.
Proceedings of the International Conference on Machine Learning, 2023

CUDA: Convolution-Based Unlearnable Datasets.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Implicit Balancing and Regularization: Generalization and Convergence Guarantees for Overparameterized Asymmetric Matrix Sensing.
Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022
Convergence and Sample Complexity of Gradient Methods for the Model-Free Linear-Quadratic Regulator Problem.
IEEE Trans. Autom. Control., 2022

SMILE: Scaling Mixture-of-Experts with Efficient Bi-level Routing.
CoRR, 2022

The Geometry of Self-supervised Learning Models and its Impact on Transfer Learning.
CoRR, 2022

Neural Networks can Learn Representations with Gradient Descent.
CoRR, 2022

Toward a Geometrical Understanding of Self-supervised Contrastive Learning.
CoRR, 2022

HUMUS-Net: Hybrid unrolled multi-scale network architecture for accelerated MRI reconstruction.
CoRR, 2022

HUMUS-Net: Hybrid Unrolled Multi-scale Network Architecture for Accelerated MRI Reconstruction.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Outlier-Robust Sparse Estimation via Non-Convex Optimization.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks.
Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2022, 2022

Statistical Minimax Lower Bounds for Transfer Learning in Linear Binary Classification.
Proceedings of the IEEE International Symposium on Information Theory, 2022

On The Effectiveness of Active Learning by Uncertainty Sampling in Classification of High-Dimensional Gaussian Mixture Data.
Proceedings of the IEEE International Conference on Acoustics, 2022

Neural Networks can Learn Representations with Gradient Descent.
Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

2021
On the Linear Convergence of Random Search for Discrete-Time LQR.
IEEE Control. Syst. Lett., 2021

FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks.
CoRR, 2021

SSFL: Tackling Label Deficiency in Federated Learning via Personalized Self-Supervision.
CoRR, 2021

A Field Guide to Federated Optimization.
CoRR, 2021

FedNLP: A Research Platform for Federated Learning in Natural Language Processing.
CoRR, 2021

Understanding Overparameterization in Generative Adversarial Networks.
CoRR, 2021

PipeTransformer: Automated Elastic Pipelining for Distributed Training of Transformers.
CoRR, 2021

Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Generalization Guarantees for Neural Architecture Search with Train-Validation Split.
Proceedings of the 38th International Conference on Machine Learning, 2021

Data augmentation for deep learning based accelerated MRI reconstruction with limited data.
Proceedings of the 38th International Conference on Machine Learning, 2021

PipeTransformer: Automated Elastic Pipelining for Distributed Training of Large-scale Models.
Proceedings of the 38th International Conference on Machine Learning, 2021

Understanding Over-parameterization in Generative Adversarial Networks.
Proceedings of the 9th International Conference on Learning Representations, 2021

On the lack of gradient domination for linear quadratic Gaussian problems with incomplete state information.
Proceedings of the 2021 60th IEEE Conference on Decision and Control (CDC), 2021

2020
Toward Moderate Overparameterization: Global Convergence Guarantees for Training Shallow Neural Networks.
IEEE J. Sel. Areas Inf. Theory, 2020

Precise Statistical Analysis of Classification Accuracies for Adversarial Training.
CoRR, 2020

Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximation.
CoRR, 2020

Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Learning the model-free linear quadratic regulator via random search.
Proceedings of the 2nd Annual Conference on Learning for Dynamics and Control, 2020

Compressive sensing with un-trained neural networks: Gradient descent finds a smooth approximation.
Proceedings of the 37th International Conference on Machine Learning, 2020

High-dimensional Robust Mean Estimation via Gradient Descent.
Proceedings of the 37th International Conference on Machine Learning, 2020

Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators.
Proceedings of the 8th International Conference on Learning Representations, 2020

3D Phase Retrieval at Nano-Scale via Accelerated Wirtinger Flow.
Proceedings of the 28th European Signal Processing Conference, 2020

Precise Tradeoffs in Adversarial Training for Linear Regression.
Proceedings of the Conference on Learning Theory, 2020

Approximation Schemes for ReLU Regression.
Proceedings of the Conference on Learning Theory, 2020

Random search for learning the linear quadratic regulator.
Proceedings of the 2020 American Control Conference, 2020

Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019
Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks.
IEEE Trans. Inf. Theory, 2019

Structured Signal Recovery From Quadratic Measurements: Breaking Sample Complexity Barriers via Nonconvex Optimization.
IEEE Trans. Inf. Theory, 2019

Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian.
CoRR, 2019

Towards moderate overparameterization: global convergence guarantees for training shallow neural networks.
CoRR, 2019

Fitting ReLUs via SGD and Quantized SGD.
Proceedings of the IEEE International Symposium on Information Theory, 2019

Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?
Proceedings of the 36th International Conference on Machine Learning, 2019

Global exponential convergence of gradient methods over the nonconvex landscape of the linear quadratic regulator.
Proceedings of the 58th IEEE Conference on Decision and Control, 2019

Lagrange Coded Computing: Optimal Design for Resiliency, Security, and Privacy.
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

Generalization, Adaptation and Low-Rank Representation in Neural Networks.
Proceedings of the 53rd Asilomar Conference on Signals, Systems, and Computers, 2019

2018
Sharp Time-Data Tradeoffs for Linear Inverse Problems.
IEEE Trans. Inf. Theory, 2018

Generalized Line Spectral Estimation via Convex Optimization.
IEEE Trans. Inf. Theory, 2018

Polynomially Coded Regression: Optimal Straggler Mitigation via Data Encoding.
CoRR, 2018

End-to-end Learning of a Convolutional Neural Network via Deep Tensor Decomposition.
CoRR, 2018

Fundamental Resource Trade-offs for Encoded Distributed Optimization.
CoRR, 2018

Near-Optimal Straggler Mitigation for Distributed Gradient Methods.
Proceedings of the 2018 IEEE International Parallel and Distributed Processing Symposium Workshops, 2018

Accelerated Wirtinger Flow for Multiplexed Fourier Ptychographic Microscopy.
Proceedings of the 2018 IEEE International Conference on Image Processing, 2018

2017
Fast and Reliable Parameter Estimation from Nonlinear Observations.
SIAM J. Optim., 2017

Learning ReLUs via Gradient Descent.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Gradient Methods for Submodular Maximization.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

2016
Low-rank Solutions of Linear Matrix Equations via Procrustes Flow.
Proceedings of the 33nd International Conference on Machine Learning, 2016

2015
Phase Retrieval via Wirtinger Flow: Theory and Algorithms.
IEEE Trans. Inf. Theory, 2015

Experimental robustness of Fourier Ptychography phase retrieval algorithms.
CoRR, 2015

Isometric sketching of any set via the Restricted Isometry Property.
CoRR, 2015

2014
Super-Resolution Radar.
CoRR, 2014

2013
Robust Subspace Clustering
CoRR, 2013

Phase Retrieval from masked Fourier transforms.
CoRR, 2013

2012
A unified approach to sparse signal processing.
EURASIP J. Adv. Signal Process., 2012

Discussion: Latent variable graphical model selection via convex optimization
CoRR, 2012

2011
A Geometric Analysis of Subspace Clustering with Outliers
CoRR, 2011

2009
A Unified Approach to Sparse Signal Processing
CoRR, 2009

A practical sparse channel estimation for current OFDM standards.
Proceedings of the 2009 International Conference on Telecommunications, 2009

Errorless Codes for Over-Loaded CDMA with Active User Detection.
Proceedings of IEEE International Conference on Communications, 2009

OFDM channel estimation based on Adaptive Thresholding for Sparse Signal Detection.
Proceedings of the 17th European Signal Processing Conference, 2009

2008
Salt and pepper noise removal for image signals.
Proceedings of the 2008 International Conference on Telecommunications, 2008


  Loading...