Broadcast Product: Shape-aligned Element-wise Multiplication and Beyond
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929516115394560 |
|---|---|
| author | Matsui, Yusuke Yokota, Tatsuya |
| author_facet | Matsui, Yusuke Yokota, Tatsuya |
| contents | We propose a new operator defined between two tensors, the broadcast product. The broadcast product calculates the Hadamard product after duplicating elements to align the shapes of the two tensors. Complex tensor operations in libraries like \texttt{numpy} can be succinctly represented as mathematical expressions using the broadcast product. Finally, we propose a novel tensor decomposition using the broadcast product, highlighting its potential applications in dimensionality reduction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_17502 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Broadcast Product: Shape-aligned Element-wise Multiplication and Beyond Matsui, Yusuke Yokota, Tatsuya Machine Learning We propose a new operator defined between two tensors, the broadcast product. The broadcast product calculates the Hadamard product after duplicating elements to align the shapes of the two tensors. Complex tensor operations in libraries like \texttt{numpy} can be succinctly represented as mathematical expressions using the broadcast product. Finally, we propose a novel tensor decomposition using the broadcast product, highlighting its potential applications in dimensionality reduction. |
| title | Broadcast Product: Shape-aligned Element-wise Multiplication and Beyond |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2409.17502 |