Efficient Implementation of LinearUCB through Algorithmic Improvements and Vector Computing Acceleration for Embedded Learning Systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909464205983744 |
|---|---|
| author | Angioli, Marco Barbirotta, Marcello Cheikh, Abdallah Mastrandrea, Antonio Menichelli, Francesco Olivieri, Mauro |
| author_facet | Angioli, Marco Barbirotta, Marcello Cheikh, Abdallah Mastrandrea, Antonio Menichelli, Francesco Olivieri, Mauro |
| contents | As the Internet of Things expands, embedding Artificial Intelligence algorithms in resource-constrained devices has become increasingly important to enable real-time, autonomous decision-making without relying on centralized cloud servers. However, implementing and executing complex algorithms in embedded devices poses significant challenges due to limited computational power, memory, and energy resources. This paper presents algorithmic and hardware techniques to efficiently implement two LinearUCB Contextual Bandits algorithms on resource-constrained embedded devices. Algorithmic modifications based on the Sherman-Morrison-Woodbury formula streamline model complexity, while vector acceleration is harnessed to speed up matrix operations. We analyze the impact of each optimization individually and then combine them in a two-pronged strategy. The results show notable improvements in execution time and energy consumption, demonstrating the effectiveness of combining algorithmic and hardware optimizations to enhance learning models for edge computing environments with low-power and real-time requirements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_13139 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient Implementation of LinearUCB through Algorithmic Improvements and Vector Computing Acceleration for Embedded Learning Systems Angioli, Marco Barbirotta, Marcello Cheikh, Abdallah Mastrandrea, Antonio Menichelli, Francesco Olivieri, Mauro Machine Learning Hardware Architecture As the Internet of Things expands, embedding Artificial Intelligence algorithms in resource-constrained devices has become increasingly important to enable real-time, autonomous decision-making without relying on centralized cloud servers. However, implementing and executing complex algorithms in embedded devices poses significant challenges due to limited computational power, memory, and energy resources. This paper presents algorithmic and hardware techniques to efficiently implement two LinearUCB Contextual Bandits algorithms on resource-constrained embedded devices. Algorithmic modifications based on the Sherman-Morrison-Woodbury formula streamline model complexity, while vector acceleration is harnessed to speed up matrix operations. We analyze the impact of each optimization individually and then combine them in a two-pronged strategy. The results show notable improvements in execution time and energy consumption, demonstrating the effectiveness of combining algorithmic and hardware optimizations to enhance learning models for edge computing environments with low-power and real-time requirements. |
| title | Efficient Implementation of LinearUCB through Algorithmic Improvements and Vector Computing Acceleration for Embedded Learning Systems |
| topic | Machine Learning Hardware Architecture |
| url | https://arxiv.org/abs/2501.13139 |