Pith. sign in

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 1

years

2025 1

verdicts

CONDITIONAL 1

roles

baseline 1

polarities

baseline 1

representative citing papers

FERRET: Private Deep Learning Faster And Better Than DPSGD

cs.CR · 2025-06-04 · conditional · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • FERRET: Private Deep Learning Faster And Better Than DPSGD cs.CR · 2025-06-04 · conditional · none · ref 3

    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.