activity
20242026
collaborators

12 papers

cs.LG2026

Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping

Hsun-Yu Kuo, El Mahdi Chayti, Patrik Reizinger +2

Looped Transformers, which repeatedly apply a shared transformer block, are an architecturally natural fit for variable-length algorithmic tasks. Although they can exhibit strong l…

math.OC2026

Stochastic Zeroth-Order Optimization Under Heavy-Tailed Noise

Taha El Bakkali, El Mahdi Chayti, Qiuyi Zhang +2

We study stochastic zeroth-order (ZO) optimization of smooth nonconvex objectives under heavy-tailed sample-gradient noise. This regime is motivated by empirical evidence that grad…

math.OC2026

Stochastic Compositional Optimization via Hybrid Momentum Frank--Wolfe

El Mahdi Chayti

Stochastic compositional optimization minimizes objectives of the form , where is accessible only through noisy st…

math.OC2026

Nonsmooth Optimization with Zeroth Order Comparison Feedback

Taha El Bakkali, El Mahdi Chayti, Omar Saadi

We study unconstrained optimization problems of nonsmooth, nonconvex Lipschitz functions, using only noisy pairwise comparisons governed by a known link function. Our goal is to co…

math.OC2026

RanSOM: Second-Order Momentum with Randomized Scaling for Constrained and Unconstrained Optimization

El Mahdi Chayti

Momentum methods, such as Polyak's Heavy Ball, are the standard for training deep networks but suffer from curvature-induced bias in stochastic settings, limiting convergence to su…

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…