activity
20122026
most citedLow-Rank Tensor Networks for Dimensionality Reduction and Large-Scale Optimization Problems: Perspectives and Challenges PART 1

466 citations · 881 across the 30 of their papers we have counts for

collaborators

32 papers

math.NA2026

A New Tensor Network: Tubal Tensor Train and Its Applications

Salman Ahmadi-Asl, Valentin Leplat, Anh-Huy Phan +1

We introduce the tubal tensor train (TTT) decomposition, a tensor-network model that combines the t-product algebra of the tensor singular value decomposition (T-SVD) with the low-…

math.NA2025

Nonnegative Tensor Decomposition Via Collaborative Neurodynamic Optimization

Salman Ahmadi-Asl, Valentin Leplat, Anh-Huy Phan +1

This paper introduces a novel collaborative neurodynamic model for computing nonnegative Canonical Polyadic Decomposition (CPD). The model relies on a system of recurrent neural ne…

cs.LG2023

TERM Model: Tensor Ring Mixture Model for Density Estimation

Ruituo Wu, Jiani Liu, Ce Zhu +3

Efficient probability density estimation is a core challenge in statistical machine learning. Tensor-based probabilistic graph methods address interpretability and stability concer…

cs.LG2023

Quantization Aware Factorization for Deep Neural Network Compression

Daria Cherniuk, Stanislav Abukhovich, Anh-Huy Phan +3

Tensor decomposition of convolutional and fully-connected layers is an effective way to reduce parameters and FLOP in neural networks. Due to memory and power consumption limitatio…

cs.CV2023★ 1 cited

Lightweight Attribute Localizing Models for Pedestrian Attribute Recognition

Ashish Jha, Dimitrii Ermilov, Konstantin Sobolev +8

Pedestrian Attribute Recognition (PAR) focuses on identifying various attributes in pedestrian images, with key applications in person retrieval, suspect re-identification, and sof…

cs.CV2023

Image Reconstruction using Superpixel Clustering and Tensor Completion

Maame G. Asante-Mensah, Anh Huy Phan, Salman Ahmadi-Asl +2

This paper presents a pixel selection method for compact image representation based on superpixel segmentation and tensor completion. Our method divides the image into several regi…