activity
20192026
most citedRandom Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures

20 citations · 32 across the 12 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2025

-LoRA: Effective Fine-Tuning via Base Model Rescaling

Aymane El Firdoussi, El Mahdi Chayti, Mohamed El Amine Seddik +1

Fine-tuning has proven to be highly effective in adapting pre-trained models to perform better on new desired tasks with minimal data samples. Among the most widely used approaches…

cs.LG2025

On the Stability of the Jacobian Matrix in Deep Neural Networks

Benjamin Dadoun, Soufiane Hayou, Hanan Salam +2

Deep neural networks are known to suffer from exploding or vanishing gradients as depth increases, a phenomenon closely tied to the spectral behavior of the input-output Jacobian.…

cs.LG2025

Accurate and Diverse LLM Mathematical Reasoning via Automated PRM-Guided GFlowNets

Adam Younsi, Ahmed Attia, Abdalgader Abubaker +3

Achieving both accuracy and diverse reasoning remains challenging for Large Language Models (LLMs) in complex domains like mathematics. A key bottleneck is evaluating intermediate…

cs.LG2024

Maximizing the Potential of Synthetic Data: Insights from Random Matrix Theory

Aymane El Firdoussi, Mohamed El Amine Seddik, Soufiane Hayou +3

Synthetic data has gained attention for training large language models, but poor-quality data can harm performance (see, e.g., Shumailov et al. (2023); Seddik et al. (2024)). A pot…

cs.LG2024

High-dimensional Learning with Noisy Labels

Aymane El Firdoussi, Mohamed El Amine Seddik

This paper provides theoretical insights into high-dimensional binary classification with class-conditional noisy labels. Specifically, we study the behavior of a linear classifier…

cs.LG20243 cited

How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapse

Mohamed El Amine Seddik, Suei-Wen Chen, Soufiane Hayou +2

The phenomenon of model collapse, introduced in (Shumailov et al., 2023), refers to the deterioration in performance that occurs when new models are trained on synthetic data gener…