ZO-MOPI accelerates zeroth-order LLM fine-tuning by applying partial spectral orthogonalization from power iteration inside a momentum-projected subspace to reduce variance and exploit dominant directions.
Our method reaches the highest accuracy of 91.7%, with almost the same wall-clock time and slightly additional memory usage
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
No citing papers match the current filters.