16 citations · 31 across the 4 of their papers we have counts for
5 papers
Distribution-Aware Tensor Decomposition for Compression of Convolutional Neural Networks
Alper Kalle, Theo Rudkiewicz, Mohamed-Oumar Ouerfelli +1
Neural networks are widely used for image-related tasks but typically demand considerable computing power. Once a network has been trained, however, its memory- and compute-footpri…
The Tensor Track VII: From Quantum Gravity to Artificial Intelligence
Mohamed Ouerfelli, Vincent Rivasseau, Mohamed Tamaazousti
Assuming some familiarity with quantum field theory and with the tensor track approach that one of us presented in the previous series Tensor Track I to VI, we provide, as usual, t…
Selective Multiple Power Iteration: from Tensor PCA to gradient-based exploration of landscapes
Mohamed Ouerfelli, Mohamed Tamaazousti, Vincent Rivasseau
We propose Selective Multiple Power Iterations (SMPI), a new algorithm to address the important Tensor PCA problem that consists in recovering a spike corrup…
Functional renormalization group for multilinear disordered Langevin dynamics I: Formalism and first numerical investigations at equilibrium
Vincent Lahoche, Dine Ousmane Samary, Mohamed Ouerfelli
This paper aims at using the functional renormalization group formalism to study the equilibrium states of a stochastic process described by a quench--disordered multilinear Langev…
Field theoretical approach for signal detection in nearly continuous positive spectra II: Tensorial data
Vincent Lahoche, Mohamed Ouerfelli, Dine Ousmane Samary +1
The tensorial principal component analysis is a generalization of ordinary principal component analysis, focusing on data which are suitably described by tensors rather than matric…