FERRET trains models with sparsely released 1-bit random projections, bounding privacy by mutual information, and reports better perplexity and speed than DPSGD on five small LLMs.
Signsgd: Compressed optimisation for non-convex problems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
FERRET: Private Deep Learning Faster And Better Than DPSGD
FERRET trains models with sparsely released 1-bit random projections, bounding privacy by mutual information, and reports better perplexity and speed than DPSGD on five small LLMs.