Adding a 'granularity' reshape to low-rank gradient projection improves memory efficiency and, in most tested settings, accuracy at a fixed memory cost.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Memory-Efficient LLM Training by Various-Grained Low-Rank Projection of Gradients
Adding a 'granularity' reshape to low-rank gradient projection improves memory efficiency and, in most tested settings, accuracy at a fixed memory cost.