Decentralized Communication-Efficient Multi-Task Representation Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2022
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918130302844928 |
|---|---|
| author | Moothedath, Shana Vaswani, Namrata |
| author_facet | Moothedath, Shana Vaswani, Namrata |
| contents | This work develops a provably accurate fully-decentralized alternating projected gradient descent (GD) algorithm for recovering a low rank (LR) matrix from mutually independent projections of each of its columns, in a fast and communication-efficient fashion. To our best knowledge, this work is the first attempt to develop a provably correct decentralized algorithm (i) for any problem involving the use of an alternating projected GD algorithm; (ii) and for any problem in which the constraint set to be projected to is a non-convex set. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2204_08117 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Decentralized Communication-Efficient Multi-Task Representation Learning Moothedath, Shana Vaswani, Namrata Information Theory This work develops a provably accurate fully-decentralized alternating projected gradient descent (GD) algorithm for recovering a low rank (LR) matrix from mutually independent projections of each of its columns, in a fast and communication-efficient fashion. To our best knowledge, this work is the first attempt to develop a provably correct decentralized algorithm (i) for any problem involving the use of an alternating projected GD algorithm; (ii) and for any problem in which the constraint set to be projected to is a non-convex set. |
| title | Decentralized Communication-Efficient Multi-Task Representation Learning |
| topic | Information Theory |
| url | https://arxiv.org/abs/2204.08117 |