2 papers
stat.ML2026
Whitening Spherical Gaussian Mixtures in the Large-Dimensional Regime
Mohammed Racim Moussa Boudjemaa, Alper Kalle, Xiaoyi Mai +2
Whitening is a classical technique in unsupervised learning that can facilitate estimation tasks by standardizing data. An important application is the estimation of latent variabl…
cs.LG2025
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…