activity
20242026
collaborators

9 papers

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

stat.ML2025

Learning quadratic neural networks in high dimensions: SGD dynamics and scaling laws

Gérard Ben Arous, Murat A. Erdogdu, Nuri Mert Vural +1

We study the optimization and sample complexity of gradient-based training of a two-layer neural network with quadratic activation function in the high-dimensional regime, where th…

cs.LG2025

Distributional Training Data Attribution: What do Influence Functions Sample?

Bruno Mlodozeniec, Isaac Reid, Sam Power +4

Randomness is an unavoidable part of training deep learning models, yet something that traditional training data attribution algorithms fail to rigorously account for. They ignore…

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…

math.ST2025

A Geometric Analysis of PCA

Ayoub El Hanchi, Murat Erdogdu, Chris Maddison

What property of the data distribution determines the excess risk of principal component analysis? In this paper, we provide a precise answer to this question. We establish a centr…

stat.ML2025

Robust Feature Learning for Multi-Index Models in High Dimensions

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

Recently, there have been numerous studies on feature learning with neural networks, specifically on learning single- and multi-index models where the target is a function of a low…