Methods › General › Data Parallel Methods › PowerSGD
PowerSGD
Introduced by Thijs Vogels et al. in PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
PowerSGD is a distributed optimization technique that computes a low-rank approximation of the gradient using a generalized power iteration (known as subspace iteration). The approximation is computationally light-weight, avoiding any prohibitively expensive Singular Value Decomposition. To improve the quality of the efficient approximation, the authors warm-start the power iteration by reusing the approximation from the previous optimization step.
Papers archive 2025-07-28
3 shown of 3, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Practical Low-Rank Communication Compression in Decentralized Deep Learning 1 Dec 2020 · 1 repository
-
PowerGossip: Practical Low-Rank Communication Compression in Decentralized Deep Learning 4 Aug 2020 · 1 repository · arXiv:2008.01425Syntology ran 3 of 3 samples · 0 unverified · 2 pointer-only (licence)
-
PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization 31 May 2019 · 1 repository · arXiv:1905.13727Syntology ran 3 of 3 samples · 0 unverified
Tasks archive 2025-07-28
2 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Deep Learning | 2 |
| Distributed Optimization | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections