A New Class of Geometric Analog Error Correction Codes for Crossbar Based In-Memory Computing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914609311514624 |
|---|---|
| author | Zhu, Ziyuan Yuan, Changcheng Roth, Ron M. Siegel, Paul H. Jiang, Anxiao |
| author_facet | Zhu, Ziyuan Yuan, Changcheng Roth, Ron M. Siegel, Paul H. Jiang, Anxiao |
| contents | Analog error correction codes have been proposed for analog in-memory computing on resistive crossbars, which can accelerate vector-matrix multiplication for machine learning. Unlike traditional communication or storage channels, this setting involves a mixed noise model with small perturbations and outlier errors. A number of analog codes have been proposed for handling a single outlier, and several constructions have also been developed to address multiple outliers. However, the set of available code families remains limited, covering only a narrow range of code lengths and dimensions. In this paper, we study a recently proposed family of geometric codes capable of handling multiple outliers, and develop a geometric analysis that characterizes their m-height profiles. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03723 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A New Class of Geometric Analog Error Correction Codes for Crossbar Based In-Memory Computing Zhu, Ziyuan Yuan, Changcheng Roth, Ron M. Siegel, Paul H. Jiang, Anxiao Information Theory Analog error correction codes have been proposed for analog in-memory computing on resistive crossbars, which can accelerate vector-matrix multiplication for machine learning. Unlike traditional communication or storage channels, this setting involves a mixed noise model with small perturbations and outlier errors. A number of analog codes have been proposed for handling a single outlier, and several constructions have also been developed to address multiple outliers. However, the set of available code families remains limited, covering only a narrow range of code lengths and dimensions. In this paper, we study a recently proposed family of geometric codes capable of handling multiple outliers, and develop a geometric analysis that characterizes their m-height profiles. |
| title | A New Class of Geometric Analog Error Correction Codes for Crossbar Based In-Memory Computing |
| topic | Information Theory |
| url | https://arxiv.org/abs/2603.03723 |