| 2026 | COLT | When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks. | Berk Tinaz, Changzhi Xie, Mahdi Soltanolkotabi |
| 2025 | CVPR | HARMONY: Hidden Activation Representations and Model Output-Aware Uncertainty Estimation for Vision-Language Models. | Erum Mushtaq, Zalan Fabian, Yavuz Faruk Bakman, Anil Ramakrishna, Mahdi Soltanolkotabi, Salman Avestimehr |
| 2025 | ICIP | Learning from PU Data Using Disentangled Representations. | Omar Zamzam, Haleh Akrami, Mahdi Soltanolkotabi, Richard M. Leahy |
| 2025 | ICLR | MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models. | Mohammad Shahab Sepehri, Zalan Fabian, Maryam Soltanolkotabi, Mahdi Soltanolkotabi |
| 2025 | ICML | Test-Time Training Provably Improves Transformers as In-context Learners. | Halil Alperen Gozeten, Muhammed Emrullah Ildiz, Xuechen Zhang, Mahdi Soltanolkotabi, Marco Mondelli, Samet Oymak |
| 2024 | ICML | Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks. | Liam Collins, Hamed Hassani, Mahdi Soltanolkotabi, Aryan Mokhtari, Sanjay Shakkottai |
| 2024 | ICML | Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models. | Zalan Fabian, Berk Tinaz, Mahdi Soltanolkotabi |
| 2024 | ICML | DiracDiffusion: Denoising and Incremental Reconstruction with Assured Data-Consistency. | Zalan Fabian, Berk Tinaz, Mahdi Soltanolkotabi |
| 2023 | COLT | Implicit Balancing and Regularization: Generalization and Convergence Guarantees for Overparameterized Asymmetric Matrix Sensing. | Mahdi Soltanolkotabi, Dominik Stger, Changzhi Xie |
| 2023 | CVPR | CUDA: Convolution-Based Unlearnable Datasets. | Vinu Sankar Sadasivan, Mahdi Soltanolkotabi, Soheil Feizi |
| 2023 | ICML | On the Role of Attention in Prompt-tuning. | Samet Oymak, Ankit Singh Rawat, Mahdi Soltanolkotabi, Christos Thrampoulidis |
| 2022 | COLT | Neural Networks can Learn Representations with Gradient Descent. | Alexandru Damian, Jason D. Lee, Mahdi Soltanolkotabi |
| 2022 | ICASSP | On The Effectiveness of Active Learning by Uncertainty Sampling in Classification of High-Dimensional Gaussian Mixture Data. | Xiaoyi Mai, Salman Avestimehr, Antonio Ortega, Mahdi Soltanolkotabi |
| 2022 | ISIT | Statistical Minimax Lower Bounds for Transfer Learning in Linear Binary Classification. | Seyed Mohammadreza Mousavi Kalan, Mahdi Soltanolkotabi, Amir Salman Avestimehr |
| 2022 | NAACL | FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks. | Bill Yuchen Lin, Chaoyang He, Zihang Ze, Hulin Wang, Yufen Hua, Christophe Dupuy, Rahul Gupta, Mahdi Soltanolkotabi, Xiang Ren, Salman Avestimehr |
| 2021 | ICLR | Understanding Over-parameterization in Generative Adversarial Networks. | Yogesh Balaji, Mohammadmahdi Sajedi, Neha Mukund Kalibhat, Mucong Ding, Dominik Stger, Mahdi Soltanolkotabi, Soheil Feizi |
| 2021 | ICML | PipeTransformer: Automated Elastic Pipelining for Distributed Training of Large-scale Models. | Chaoyang He, Shen Li, Mahdi Soltanolkotabi, Salman Avestimehr |
| 2021 | ICML | Data augmentation for deep learning based accelerated MRI reconstruction with limited data. | Zalan Fabian, Reinhard Heckel, Mahdi Soltanolkotabi |
| 2021 | ICML | Generalization Guarantees for Neural Architecture Search with Train-Validation Split. | Samet Oymak, Mingchen Li, Mahdi Soltanolkotabi |
| 2020 | AISTATS | Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks. | Mingchen Li, Mahdi Soltanolkotabi, Samet Oymak |
| 2020 | COLT | Approximation Schemes for ReLU Regression. | Ilias Diakonikolas, Surbhi Goel, Sushrut Karmalkar, Adam R. Klivans, Mahdi Soltanolkotabi |
| 2020 | COLT | Precise Tradeoffs in Adversarial Training for Linear Regression. | Adel Javanmard, Mahdi Soltanolkotabi, Hamed Hassani |
| 2020 | ICLR | Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators. | Reinhard Heckel, Mahdi Soltanolkotabi |
| 2020 | ICML | High-dimensional Robust Mean Estimation via Gradient Descent. | Yu Cheng, Ilias Diakonikolas, Rong Ge, Mahdi Soltanolkotabi |
| 2020 | ICML | Compressive sensing with un-trained neural networks: Gradient descent finds a smooth approximation. | Reinhard Heckel, Mahdi Soltanolkotabi |
| 2019 | ACSSC | Generalization, Adaptation and Low-Rank Representation in Neural Networks. | Samet Oymak, Zalan Fabian, Mingchen Li, Mahdi Soltanolkotabi |
| 2019 | AISTATS | Lagrange Coded Computing: Optimal Design for Resiliency, Security, and Privacy. | Qian Yu, Songze Li, Netanel Raviv, Seyed Mohammadreza Mousavi Kalan, Mahdi Soltanolkotabi, Amir Salman Avestimehr |
| 2019 | ICML | Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path? | Samet Oymak, Mahdi Soltanolkotabi |
| 2019 | ISIT | Fitting ReLUs via SGD and Quantized SGD. | Seyed Mohammadreza Mousavi Kalan, Mahdi Soltanolkotabi, Amir Salman Avestimehr |
| 2018 | ICIP | Accelerated Wirtinger Flow for Multiplexed Fourier Ptychographic Microscopy. | Emrah Bostan, Mahdi Soltanolkotabi, David Ren, Laura Waller |
| 2016 | ICML | Low-rank Solutions of Linear Matrix Equations via Procrustes Flow. | Stephen Tu, Ross Boczar, Max Simchowitz, Mahdi Soltanolkotabi, Ben Recht |