Search Results - "Seddik, Mohamed El Amine"

Learning More Universal Representations for Transfer-Learning by Tamaazousti, Youssef, Le Borgne, Herve, Hudelot, Celine, Seddik, Mohamed-El-Amine, Tamaazousti, Mohamed

“…A representation is supposed universal if it encodes any element of the visual world (e.g., objects, scenes) in any configuration (e.g., scale, context). While…”
Get full text

Soil Moisture Estimation Using Sentinel-1/-2 Imagery Coupled With CycleGAN for Time-Series Gap Filing by Efremova, Natalia, Seddik, Mohamed El Amine, Erten, Esra

“…Fast soil moisture content (SMC) mapping is necessary to support water resource management and to understand crop growth, quality, and yield. Therefore, earth…”
Get full text

Kernel Random Matrices of Large Concentrated Data: the Example of GAN-Generated Images by Amine Seddik, Mohamed El, Tamaazousti, Mohamed, Couillet, Romain

“…Based on recent random matrix advances in the analysis of kernel methods for classification and clustering, this paper proposes the study of large kernel…”
Get full text

Optimization-Based Neural Networks Compression by Tahiri, Younes, Seddik, Mohamed El Amine, Tamaazousti, Mohamed

“…This paper presents a method for constructing a size compressed neural network with better or similar accuracy than a given dense neural network, therefore the…”
Get full text

From outage probability to ALOHA MAC layer performance analysis in distributed WSNs by Seddik, Mohamed-El-Amine, Toldov, Viktor, Clavier, Laurent, Mitton, Nathalie

“…In cellular networks, the outage probability is the probability that the signal-to-interference-plus-noise-ratio (SINR) is less than a given threshold. In this…”
Get full text

When random tensors meet random matrices by Seddik, Mohamed El Amine, Guillaud, Maxime, Couillet, Romain

“…Relying on random matrix theory (RMT), this paper studies asymmetric order-d spiked tensor models with Gaussian noise. Using the variational definition of the…”
Get full text

Generative collaborative networks for single image super-resolution by Seddik, Mohamed El Amine, Tamaazousti, Mohamed, Lin, John

“…A common issue of deep neural networks-based methods for the problem of Single Image Super-Resolution (SISR), is the recovery of finer texture details when…”
Get full text

Lightweight Neural Networks From PCA & LDA Based Distilled Dense Neural Networks by Seddik, Mohamed El Amine, Essafi, Hassane, Benzine, Abdallah, Tamaazousti, Mohamed

“…This paper presents two methods for building lightweight neural networks with similar accuracy than heavyweight ones with the advantage to be less greedy in…”
Get full text

High-dimensional Learning with Noisy Labels by Firdoussi, Aymane El, Seddik, Mohamed El Amine

“…This paper provides theoretical insights into high-dimensional binary classification with class-conditional noisy labels. Specifically, we study the behavior…”
Get full text

A Nested Matrix-Tensor Model for Noisy Multi-view Clustering by Seddik, Mohamed El Amine, Achab, Mastane, Goulart, Henrique, Debbah, Merouane

“…In this paper, we propose a nested matrix-tensor model which extends the spiked rank-one tensor model of order three. This model is particularly motivated by a…”
Get full text

Optimizing Orthogonalized Tensor Deflation via Random Tensor Theory by Seddik, Mohamed El Amine, Mahfoud, Mohammed, Debbah, Merouane

“…This paper tackles the problem of recovering a low-rank signal tensor with possibly correlated components from a random noisy tensor, or so-called spiked…”
Get full text

Maximizing the Potential of Synthetic Data: Insights from Random Matrix Theory by Firdoussi, Aymane El, Seddik, Mohamed El Amine, Hayou, Soufiane, Alami, Reda, Alzubaidi, Ahmed, Hacid, Hakim

“…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…”
Get full text

Alignment with Preference Optimization Is All You Need for LLM Safety by Alami, Reda, Almansoori, Ali Khalifa, Alzubaidi, Ahmed, Seddik, Mohamed El Amine, Farooq, Mugariya, Hacid, Hakim

“…We demonstrate that preference optimization methods can effectively enhance LLM safety. Applying various alignment techniques to the Falcon 11B model using…”
Get full text

On the Accuracy of Hotelling-Type Tensor Deflation: A Random Tensor Analysis by Seddik, Mohamed El Amine, Guillaud, Maxime, Decurninge, Alexis

“…Leveraging on recent advances in random tensor theory, we consider in this paper a rank-$r$ asymmetric spiked tensor model of the form $\sum_{i=1}^r \beta_i…”
Get full text

How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapse by Seddik, Mohamed El Amine, Chen, Suei-Wen, Hayou, Soufiane, Youssef, Pierre, Debbah, Merouane

“…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…”
Get full text

Investigating Regularization of Self-Play Language Models by Alami, Reda, Abubaker, Abdalgader, Achab, Mastane, Seddik, Mohamed El Amine, Lahlou, Salem

“…This paper explores the effects of various forms of regularization in the context of language model alignment via self-play. While both reinforcement learning…”
Get full text

Performance Gaps in Multi-view Clustering under the Nested Matrix-Tensor Model by Lebeau, Hugo, Seddik, Mohamed El Amine, Goulart, José Henrique de Morais

“…We study the estimation of a planted signal hidden in a recently introduced nested matrix-tensor model, which is an extension of the classical spiked rank-one…”
Get full text

On the Accuracy of Hotelling-Type Asymmetric Tensor Deflation: A Random Tensor Analysis by Seddik, Mohamed El Amine, Guillaud, Maxime, Decurninge, Alexis, Goulart, José Henrique de Morais

“…This work introduces an asymptotic study of Hotelling-type tensor deflation in the presence of noise, in the regime of large tensor dimensions. Specifically,…”
Get full text

When Random Tensors meet Random Matrices by Seddik, Mohamed El Amine, Guillaud, Maxime, Couillet, Romain

“…Relying on random matrix theory (RMT), this paper studies asymmetric order-$d$ spiked tensor models with Gaussian noise. Using the variational definition of…”
Get full text

Hotelling Deflation on Large Symmetric Spiked Tensors by Seddik, Mohamed El Amine, Goulart, José Henrique de Morais, Guillaud, Maxime

“…This paper studies the deflation algorithm when applied to estimate a low-rank symmetric spike contained in a large tensor corrupted by additive Gaussian…”
Get full text