Singleshot : a scalable Tucker tensor decomposition - Archive ouverte HAL Access content directly
Conference Papers Year :

Singleshot : a scalable Tucker tensor decomposition

Abraham Traoré
  • Function : Author
  • PersonId : 1028852
Maxime Berar
Alain Rakotomamonjy


This paper introduces a new approach for the scalable Tucker decomposition problem. Given a tensor X , the algorithm proposed, named Singleshot, allows to perform the inference task by processing one subtensor drawn from X at a time. The key principle of our approach is based on the recursive computations of the gradient and on cyclic update of the latent factors involving only one single step of gradient descent. We further improve the computational efficiency of Singleshot by proposing an inexact gradient version named Singleshotinexact. The two algorithms are backed with theoretical guarantees of convergence and convergence rates under mild conditions. The scalabilty of the proposed approaches, which can be easily extended to handle some common constraints encountered in tensor decomposition (e.g non-negativity), is proven via numerical experiments on both synthetic and real data sets.
Fichier principal
Vignette du fichier
Mainpaper.pdf (514.7 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02288245 , version 1 (14-09-2019)
hal-02288245 , version 2 (26-10-2019)


  • HAL Id : hal-02288245 , version 2


Abraham Traoré, Maxime Berar, Alain Rakotomamonjy. Singleshot : a scalable Tucker tensor decomposition. Advances in Neural Information Processing Systems, Dec 2019, Vancouver, Canada. ⟨hal-02288245v2⟩
181 View
242 Download


Gmail Facebook Twitter LinkedIn More