Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Geometric Matrix Completion: A Functional View

Abstract : We propose a totally functional view of geometric matrix completion problem. Differently from existing work, we propose a novel regularization inspired from the functional map literature that is more interpretable and theoretically sound. On synthetic tasks with strong underlying geometric structure, our framework outperforms state of the art by a huge margin (two order of magnitude) demonstrating the potential of our approach. On real datasets, we achieve state-of-the-art results at a fraction of the computational effort of previous methods. Our code will be publicly available at \url{https://github.com/Not-IITian/functional_matrix_completion}
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02871840
Contributor : Abhishek Sharma <>
Submitted on : Thursday, June 18, 2020 - 9:13:26 AM
Last modification on : Sunday, October 18, 2020 - 3:30:26 AM

File

neurips_matrix_completion (1)....
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02871840, version 1

Citation

Abhishek Sharma, Maks Ovsjanikov. Geometric Matrix Completion: A Functional View. 2020. ⟨hal-02871840v1⟩

Share

Metrics

Record views

271

Files downloads

359