· 2016
Tensor Networks for Dimensionality Reduction and Large-scale Optimization: Part 1 Low-Rank Tensor Decompositions
- 187citations
- 2016year
Short summary
Tensor networks, specifically Tucker and tensor train (TT) decompositions, offer a novel approach to dimensionality reduction and large-scale optimization by leveraging low-rank approximations to combat the curse of dimensionality.
AI-generated from the title and abstract; the full text is not read.
Key points
- Tensor networks, including Tucker and TT decompositions, are presented as solutions for dimensionality reduction and large-scale optimization.
- Low-rank approximations inherent in tensor networks help overcome the 'curse of dimensionality' for complex datasets.
- The paper offers new methods for low-rank tensor network decompositions and intuitive graphical representations of operations.
- These methods allow for seamless transfer of ideas between matrix and tensor operations, aiding practical applications.
AI-generated from the title and abstract; the full text is not read.
Abstract
Modern applications in engineering and data science are increasinglybased on multidimensional data of exceedingly high volume, variety,and structural richness. However, standard machine learning algorithmstypically scale exponentially with data volume and complexityof cross-modal couplings - the so called curse of dimensionality -which is prohibitive to the analysis of large-scale, multi-modal andmulti-relational datasets. Given that such data are often efficientlyrepresented as multiway arrays or tensors, it is therefore timely andvaluable for the multidisciplinary machine learning and data analyticcommunities to review low-rank tensor decompositions and tensor networksas emerging tools for dimensionality reduction and large scaleoptimization problems. Our particular emphasis is on elucidating that,by virtue of the underlying low-rank approximations, tensor networkshave the ability to alleviate the curse of dimensionality in a numberof applied areas. In Part 1 of this monograph we provide innovativesolutions to low-rank tensor network decompositions and easy to interpretgraphical representations of the mathematical operations ontensor networks. Such a conceptual insight allows for seamless migrationof ideas from the flat-view matrices to tensor network operationsand vice versa, and provides a platform for further developments, practicalapplications, and non-Euclidean extensions. It also permits theintroduction of various tensor network operations without an explicitnotion of mathematical expressions, which may be beneficial for manyresearch communities that do not directly rely on multilinear algebra.Our focus is on the Tucker and tensor train TT decompositions andtheir extensions, and on demonstrating the ability of tensor networksto provide linearly or even super-linearly e.g., logarithmically scalablesolutions, as illustrated in detail in Part 2 of this monograph.
The authors' abstract, as published at the source., 2016
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computational Mathematics
Computational MathematicsMathematics