activity
20212026
most citedNeural Networks Efficiently Learn Low-Dimensional Representations with SGD

6 citations · 7 across the 13 of their papers we have counts for

collaborators

14 papers

cs.LG2026

Super Apriel: One Checkpoint, Many Speeds

SLAM Labs, :, Oleksiy Ostapenko +13

We release Super Apriel, a 15B-parameter supernet in which every decoder layer provides four trained mixer choices -- Full Attention (FA), Sliding Window Attention (SWA), Kimi Delt…

stat.ML2026

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

Alireza Mousavi-Hosseini, Murat A. Erdogdu

We study post-training linear autoregressive models with outcome and process rewards. Given a context , the model must predict the response …

cs.LG2025

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

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

To understand feature learning dynamics in neural networks, recent theoretical works have focused on gradient-based learning of Gaussian single-index models, where the label is a n…

cs.LG2025

Flow Matching with Semidiscrete Couplings

Alireza Mousavi-Hosseini, Stephen Y. Zhang, Michal Klein +1

Flow models parameterized as time-dependent velocity fields can generate data from noise by integrating an ODE. These models are often trained using flow matching, i.e. by sampling…

cs.LG2025

On Fitting Flow Models with Large Sinkhorn Couplings

Stephen Zhang, Alireza Mousavi-Hosseini, Michal Klein +1

Flow models transform data gradually from one modality (e.g. noise) onto another (e.g. images). Such models are parameterized by a time-dependent velocity field, trained to fit seg…

stat.ML2025

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

Alireza Mousavi-Hosseini, Clayton Sanford, Denny Wu +1

Theoretical efforts to prove advantages of Transformers in comparison with classical architectures such as feedforward and recurrent neural networks have mostly focused on represen…