Tamaazousti, Mohamed

9 publications

NeurIPS 2025 Distribution-Aware Tensor Decomposition for Compression of Convolutional Neural Networks Alper Kalle, Théo Rudkiewicz, Mohamed Ouerfelli, Mohamed Tamaazousti

CVPR 2024 Universal Robustness via Median Randomized Smoothing for Real-World Super-Resolution Zakariya Chaouai, Mohamed Tamaazousti

AAAI 2022 Neural Networks Classify Through the Class-Wise Means of Their Representations Mohamed El Amine Seddik, Mohamed Tamaazousti

AAAI 2022 Random Tensor Theory for Tensor Decomposition Mohamed Ouerfelli, Mohamed Tamaazousti, Vincent Rivasseau

AISTATS 2021 The Unexpected Deterministic and Universal Behavior of Large SoftMax Classifiers Mohamed El Amine Seddik, Cosme Louart, Romain Couillet, Mohamed Tamaazousti

ICMLW 2020 A Random Matrix Analysis of Learning with Α-Dropout Mohamed El Amine Seddik, Romain Couillet, Mohamed Tamaazousti

ICML 2020 Random Matrix Theory Proves That Deep Learning Representations of GAN-Data Behave as Gaussian Mixtures Mohamed El Amine Seddik, Cosme Louart, Mohamed Tamaazousti, Romain Couillet

ICLR 2019 A Kernel Random Matrix-Based Approach for Sparse PCA Mohamed El Amine Seddik, Mohamed Tamaazousti, Romain Couillet

CVPR 2011 NonLinear Refinement of Structure from Motion Reconstruction by Taking Advantage of a Partial Knowledge of the Environment Mohamed Tamaazousti, Vincent Gay-Bellile, Sylvie Naudet-Collette, Steve Bourgeois, Michel Dhome