Distributed Tomographic Reconstruction with Quantization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929533402218496 |
|---|---|
| author | Miao, Runxuan Aslan, Selin Koyuncu, Erdem Gürsoy, Doğa |
| author_facet | Miao, Runxuan Aslan, Selin Koyuncu, Erdem Gürsoy, Doğa |
| contents | Conventional tomographic reconstruction typically depends on centralized servers for both data storage and computation, leading to concerns about memory limitations and data privacy. Distributed reconstruction algorithms mitigate these issues by partitioning data across multiple nodes, reducing server load and enhancing privacy. However, these algorithms often encounter challenges related to memory constraints and communication overhead between nodes. In this paper, we introduce a decentralized Alternating Directions Method of Multipliers (ADMM) with configurable quantization. By distributing local objectives across nodes, our approach is highly scalable and can efficiently reconstruct images while adapting to available resources. To overcome communication bottlenecks, we propose two quantization techniques based on K-means clustering and JPEG compression. Numerical experiments with benchmark images illustrate the tradeoffs between communication efficiency, memory use, and reconstruction accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_06106 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Distributed Tomographic Reconstruction with Quantization Miao, Runxuan Aslan, Selin Koyuncu, Erdem Gürsoy, Doğa Distributed, Parallel, and Cluster Computing 68W15, 65R32 Conventional tomographic reconstruction typically depends on centralized servers for both data storage and computation, leading to concerns about memory limitations and data privacy. Distributed reconstruction algorithms mitigate these issues by partitioning data across multiple nodes, reducing server load and enhancing privacy. However, these algorithms often encounter challenges related to memory constraints and communication overhead between nodes. In this paper, we introduce a decentralized Alternating Directions Method of Multipliers (ADMM) with configurable quantization. By distributing local objectives across nodes, our approach is highly scalable and can efficiently reconstruct images while adapting to available resources. To overcome communication bottlenecks, we propose two quantization techniques based on K-means clustering and JPEG compression. Numerical experiments with benchmark images illustrate the tradeoffs between communication efficiency, memory use, and reconstruction accuracy. |
| title | Distributed Tomographic Reconstruction with Quantization |
| topic | Distributed, Parallel, and Cluster Computing 68W15, 65R32 |
| url | https://arxiv.org/abs/2410.06106 |