Mousavi-Hosseini, Alireza

12 publications

NeurIPS 2025 From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD Konstantinos Christopher Tsiolis, Alireza Mousavi-Hosseini, Murat A Erdogdu

ICLR 2025 Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics Alireza Mousavi-Hosseini, Denny Wu, Murat A Erdogdu

ICLR 2025 Robust Feature Learning for Multi-Index Models in High Dimensions Alireza Mousavi-Hosseini, Adel Javanmard, Murat A Erdogdu

NeurIPS 2025 When Do Transformers Outperform Feedforward and Recurrent Networks? a Statistical Perspective Alireza Mousavi-Hosseini, Clayton Sanford, Denny Wu, Murat A Erdogdu

NeurIPS 2024 A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers Ye He, Alireza Mousavi-Hosseini, Krishnakumar Balasubramanian, Murat A. Erdogdu

ICMLW 2024 Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics Alireza Mousavi-Hosseini, Denny Wu, Murat A Erdogdu

NeurIPS 2024 Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach Guillaume Wang, Alireza Mousavi-Hosseini, Lénaïc Chizat

NeurIPSW 2024 Robust Feature Learning for Multi-Index Models in High Dimensions Alireza Mousavi-Hosseini, Adel Javanmard, Murat A Erdogdu

NeurIPS 2023 Gradient-Based Feature Learning Under Structured Data Alireza Mousavi-Hosseini, Denny Wu, Taiji Suzuki, Murat A Erdogdu

ICLR 2023 Neural Networks Efficiently Learn Low-Dimensional Representations with SGD Alireza Mousavi-Hosseini, Sejun Park, Manuela Girotti, Ioannis Mitliagkas, Murat A Erdogdu

COLT 2023 Towards a Complete Analysis of Langevin Monte Carlo: Beyond Poincaré Inequality Alireza Mousavi-Hosseini, Tyler K. Farghly, Ye He, Krishna Balasubramanian, Murat A. Erdogdu

NeurIPSW 2022 Neural Networks Efficiently Learn Low-Dimensional Representations with SGD Alireza Mousavi-Hosseini, Sejun Park, Manuela Girotti, Ioannis Mitliagkas, Murat A Erdogdu