Gradient Descent with Stochastic Subspaces via Persistence of Memory
This story is from 2026-09-17. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.18416v1 Announce Type: cross Abstract: Stochastic subspace methods have gained popularity as gradient descent based techniques for large scale optimisation problems, especially in distributed settings. In this paper, we introduce the technique of "persistence of memory" to greatly extend…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-09-17 04:00 · arXiv stat.ML
Gradient Descent with Stochastic Subspaces via Persistence of Memory