Tensor Decompositions in Deep Learning [article]

Davide Bacciu, Danilo P. Mandic
2020 arXiv   pre-print
The paper surveys the topic of tensor decompositions in modern machine learning applications. It focuses on three active research topics of significant relevance for the community. After a brief review of consolidated works on multi-way data analysis, we consider the use of tensor decompositions in compressing the parameter space of deep learning models. Lastly, we discuss how tensor methods can be leveraged to yield richer adaptive representations of complex data, including structured
more » ... on. The paper concludes with a discussion on interesting open research challenges.
arXiv:2002.11835v1 fatcat:izu4qtizqbghhnaxlhisi2tnce