Hypernetwork generates model parameters from one perturbed low-dimensional private dataset embedding, yielding higher utility than DP-SGD under fixed privacy budget in synthetic theory and lower FID in LoRA diffusion fine-tuning.
arXiv preprint arXiv:2601.11113 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Escaping Iterative Parameter-Space Noise: Differentially Private Learning with a Hypernetwork
Hypernetwork generates model parameters from one perturbed low-dimensional private dataset embedding, yielding higher utility than DP-SGD under fixed privacy budget in synthetic theory and lower FID in LoRA diffusion fine-tuning.