Alireza Mousavi-Hosseini

According to our database, Alireza Mousavi-Hosseini authored at least 14 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

Super Apriel: One Checkpoint, Many Speeds.

Oleksiy Ostapenko, Raymond Li, Torsten Scholak, Alireza Mousavi-Hosseini, Aman Tiwari, Denis Kocetkov, Joel Lamy-Poirier, Kelechi Ogueji, Nanda H. Krishna, Rafael Pardinas, Sathwik Tejaswi Madhusudhan, Shruthan Radhakrishna, Srinivas Sunkara, Valérie Bécaert

CoRR, April, 2026

Post-Training with Policy Gradients: Optimality and the Base Model Barrier.

Alireza Mousavi-Hosseini, Murat A. Erdogdu

CoRR, March, 2026

On Fitting Flow Models with Large Sinkhorn Couplings.

Stephen Y. Zhang, Alireza Mousavi-Hosseini, Michal Klein, Marco Cuturi

Trans. Mach. Learn. Res., 2026

2025

Flow Matching with Semidiscrete Couplings.

Alireza Mousavi-Hosseini, Stephen Y. Zhang, Michal Klein, Marco Cuturi

CoRR, September, 2025

When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective.

Alireza Mousavi-Hosseini, Clayton Sanford, Denny Wu, Murat A. Erdogdu

CoRR, March, 2025

From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD.

Konstantinos C. Tsiolis, Alireza Mousavi-Hosseini, Murat A. Erdogdu

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics.

Alireza Mousavi-Hosseini, Denny Wu, Murat A. Erdogdu

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Robust Feature Learning for Multi-Index Models in High Dimensions.

Alireza Mousavi-Hosseini, Adel Javanmard, Murat A. Erdogdu

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach.

Guillaume Wang, Alireza Mousavi-Hosseini, Lénaïc Chizat

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers.

Ye He, Alireza Mousavi-Hosseini, Krishnakumar Balasubramanian, Murat A. Erdogdu

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

2023

Gradient-Based Feature Learning under Structured Data.

Alireza Mousavi-Hosseini, Denny Wu, Taiji Suzuki, Murat A. Erdogdu

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Neural Networks Efficiently Learn Low-Dimensional Representations with SGD.

Alireza Mousavi-Hosseini, Sejun Park, Manuela Girotti, Ioannis Mitliagkas, Murat A. Erdogdu

Proceedings of the Eleventh International Conference on Learning Representations, 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

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2021

The Interplay between Distribution Parameters and the Accuracy-Robustness Tradeoff in Classification.

Alireza Mousavi-Hosseini, Amir Mohammad Abouei, Mohammad Hossein Rohban

CoRR, 2021