1 code implementation • 27 Mar 2024 • Jeremy E. Cohen, Valentin Leplat
However, from a practical perspective, the choice of regularizers and regularization coefficients, as well as the design of efficient algorithms, is challenging because of the multifactor nature of these models and the lack of theory to back these choices.
no code implementations • 24 Nov 2021 • Jeremy E. Cohen
Constrained tensor and matrix factorization models allow to extract interpretable patterns from multiway data.
1 code implementation • 4 Oct 2021 • Marie Roald, Carla Schenker, Vince D. Calhoun, Tülay Adalı, Rasmus Bro, Jeremy E. Cohen, Evrim Acar
We also apply our model to two real-world datasets from neuroscience and chemometrics, and show that constraining the evolving mode improves the interpretability of the extracted patterns.
2 code implementations • 3 Feb 2021 • Marie Roald, Carla Schenker, Jeremy E. Cohen, Evrim Acar
The PARAFAC2 model provides a flexible alternative to the popular CANDECOMP/PARAFAC (CP) model for tensor decompositions.
2 code implementations • 19 Jul 2020 • Carla Schenker, Jeremy E. Cohen, Evrim Acar
Coupled matrix and tensor factorizations (CMTF) are frequently used to jointly analyze data from multiple sources, also called data fusion.
1 code implementation • 13 Jun 2020 • Nicolas Nadisic, Arnaud Vandaele, Jeremy E. Cohen, Nicolas Gillis
We propose a new variant of nonnegative matrix factorization (NMF), combining separability and sparsity assumptions.
no code implementations • 13 Jan 2020 • Andersen Man Shun Ang, Jeremy E. Cohen, Nicolas Gillis, Le Thi Khanh Hien
This paper is concerned with improving the empirical convergence speed of block-coordinate descent algorithms for approximate nonnegative tensor factorization (NTF).
no code implementations • 14 Feb 2018 • Jeremy E. Cohen, Rasmus Bro
In the following manuscript, a relaxation of the PARAFAC2 model is introduced, that allows for imposing nonnegativity constraints on the varying mode.