Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.00774 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910393251659776 |
|---|---|
| author | Sun, Philip Simcha, David Dopson, Dave Guo, Ruiqi Kumar, Sanjiv |
| author_facet | Sun, Philip Simcha, David Dopson, Dave Guo, Ruiqi Kumar, Sanjiv |
| contents | This paper introduces SOAR: Spilling with Orthogonality-Amplified Residuals, a novel data indexing technique for approximate nearest neighbor (ANN) search. SOAR extends upon previous approaches to ANN search, such as spill trees, that utilize multiple redundant representations while partitioning the data to reduce the probability of missing a nearest neighbor during search. Rather than training and computing these redundant representations independently, however, SOAR uses an orthogonality-amplified residual loss, which optimizes each representation to compensate for cases where other representations perform poorly. This drastically improves the overall index quality, resulting in state-of-the-art ANN benchmark performance while maintaining fast indexing times and low memory consumption. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00774 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SOAR: Improved Indexing for Approximate Nearest Neighbor Search Sun, Philip Simcha, David Dopson, Dave Guo, Ruiqi Kumar, Sanjiv Machine Learning This paper introduces SOAR: Spilling with Orthogonality-Amplified Residuals, a novel data indexing technique for approximate nearest neighbor (ANN) search. SOAR extends upon previous approaches to ANN search, such as spill trees, that utilize multiple redundant representations while partitioning the data to reduce the probability of missing a nearest neighbor during search. Rather than training and computing these redundant representations independently, however, SOAR uses an orthogonality-amplified residual loss, which optimizes each representation to compensate for cases where other representations perform poorly. This drastically improves the overall index quality, resulting in state-of-the-art ANN benchmark performance while maintaining fast indexing times and low memory consumption. |
| title | SOAR: Improved Indexing for Approximate Nearest Neighbor Search |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2404.00774 |