Mahdi Soltanolkotabi
33 papers · 2016–2025 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
π Academic Marathon (9) π Conference Polyglot (9) π§ Keyword Pioneer π Interdisciplinary Bridge π£ Hot Topic Early Bird
π£
Hot Topic Early Bird
π§
Keyword Pioneer
π
Conference Polyglot
(9)
π
Keyword Champion
(2)
π
Triple Crown
ποΈ
Keyword Collector
(129)
β‘
Prolific Year
(5)
π
Conference Pioneer
π
Century Club
(33)
π₯
Unstoppable
(7)
β
The Questioner
(2)
Conferences
ICML (12)
NIPS (9)
COLT (4)
AISTATS (2)
ICLR (2)
CVPR (1)
JMLR (1)
L4DC (1)
NAACL (1)
Top co-authors
Research topics
Keywords
gradient descent
(11)
neural network
(3)
sample complexity
(3)
non-convex optimization
(3)
overparameterized model
(2)
image restoration
(2)
learning theory
(2)
low-rank matrix recovery
(2)
inverse problem
(2)
high-dimensional analysis
(2)
spectral method
(2)
transfer learning
(2)
federated learning
(2)
high-dimensional regime
(2)
adversarial training
(2)
linear regression
(2)
high-dimensional statistics
(2)
convolutional neural network
(2)
compressive sensing
(1)
catastrophic forgetting
(1)
Papers
MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models
ICLR 2025
Test-Time Training Provably Improves Transformers as In-context Learners
ICML 2025
DiracDiffusion: Denoising and Incremental Reconstruction with Assured Data-Consistency
ICML 2024
Learning from many trajectories
JMLR 2024
Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks
ICML 2024
Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models
ICML 2024
Implicit Balancing and Regularization: Generalization and Convergence Guarantees for Overparameterized Asymmetric Matrix Sensing
COLT 2023
Learning Provably Robust Estimators for Inverse Problems via Jittering
NIPS 2023
A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks
NIPS 2023
On the Role of Attention in Prompt-tuning
ICML 2023
CUDA: Convolution-Based Unlearnable Datasets
CVPR 2023
FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks
NAACL 2022
Neural Networks can Learn Representations with Gradient Descent
COLT 2022
HUMUS-Net: Hybrid Unrolled Multi-scale Network Architecture for Accelerated MRI Reconstruction
NIPS 2022
Outlier-Robust Sparse Estimation via Non-Convex Optimization
NIPS 2022
Understanding Over-parameterization in Generative Adversarial Networks
ICLR 2021
Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction
NIPS 2021
Data augmentation for deep learning based accelerated MRI reconstruction with limited data
ICML 2021
PipeTransformer: Automated Elastic Pipelining for Distributed Training of Large-scale Models
ICML 2021
Generalization Guarantees for Neural Architecture Search with Train-Validation Split
ICML 2021
High-dimensional Robust Mean Estimation via Gradient Descent
ICML 2020
Compressive sensing with un-trained neural networks: Gradient descent finds a smooth approximation
ICML 2020
Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks
NIPS 2020
Learning the model-free linear quadratic regulator via random search
L4DC 2020
Precise Tradeoffs in Adversarial Training for Linear Regression
COLT 2020
Approximation Schemes for ReLU Regression
COLT 2020
Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks
AISTATS 2020
Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View
NIPS 2020
Lagrange Coded Computing: Optimal Design for Resiliency, Security, and Privacy
AISTATS 2019
Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?
ICML 2019
Learning ReLUs via Gradient Descent
NIPS 2017
Gradient Methods for Submodular Maximization
NIPS 2017
Low-rank Solutions of Linear Matrix Equations via Procrustes Flow
ICML 2016