Accelerating the Low-Rank Decomposed Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909621573124096 |
|---|---|
| author | Hajimolahoseini, Habib Ahmed, Walid Wen, Austin Liu, Yang |
| author_facet | Hajimolahoseini, Habib Ahmed, Walid Wen, Austin Liu, Yang |
| contents | Tensor decomposition is a mathematically supported technique for data compression. It consists of applying some kind of a Low Rank Decomposition technique on the tensors or matrices in order to reduce the redundancy of the data. However, it is not a popular technique for compressing the AI models duo to the high number of new layers added to the architecture after decomposition. Although the number of parameters could shrink significantly, it could result in the model be more than twice deeper which could add some latency to the training or inference. In this paper, we present a comprehensive study about how to modify low rank decomposition technique in AI models so that we could benefit from both high accuracy and low memory consumption as well as speeding up the training and inference |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20266 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Accelerating the Low-Rank Decomposed Models Hajimolahoseini, Habib Ahmed, Walid Wen, Austin Liu, Yang Machine Learning Computation and Language Tensor decomposition is a mathematically supported technique for data compression. It consists of applying some kind of a Low Rank Decomposition technique on the tensors or matrices in order to reduce the redundancy of the data. However, it is not a popular technique for compressing the AI models duo to the high number of new layers added to the architecture after decomposition. Although the number of parameters could shrink significantly, it could result in the model be more than twice deeper which could add some latency to the training or inference. In this paper, we present a comprehensive study about how to modify low rank decomposition technique in AI models so that we could benefit from both high accuracy and low memory consumption as well as speeding up the training and inference |
| title | Accelerating the Low-Rank Decomposed Models |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2407.20266 |