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

3 citations · 6 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CL2026

Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes

Nan Chen, Zhouhao Yang, Soufiane Hayou

Intent classification in Large Language Models (LLMs) involves categorizing user prompts into predefined classes. For instance, given a user prompt, the system must determine wheth…

cs.LG20241 cited

The Impact of Initialization on LoRA Finetuning Dynamics

Soufiane Hayou, Nikhil Ghosh, Bin Yu

In this paper, we study the role of initialization in Low Rank Adaptation (LoRA) as originally introduced in Hu et al. (2021). Essentially, to start from the pretrained model as in…

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…

cs.NE20232 cited

Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks

Greg Yang, Dingli Yu, Chen Zhu +1

By classifying infinite-width neural networks and identifying the *optimal* limit, Tensor Programs IV and V demonstrated a universal way, called P, for *widthwise hyperparameter…

stat.ML2023

Commutative Width and Depth Scaling in Deep Neural Networks

Soufiane Hayou

This paper is the second in the series Commutative Scaling of Width and Depth (WD) about commutativity of infinite width and depth limits in deep neural networks. Our aim is to und…

stat.ML2023

On the Connection Between Riemann Hypothesis and a Special Class of Neural Networks

Soufiane Hayou

The Riemann hypothesis (RH) is a long-standing open problem in mathematics. It conjectures that non-trivial zeros of the zeta function all have real part equal to 1/2. The extent o…