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.
Private stochastic non-convex optimization: Adaptive algorithms and tighter generalization bounds
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Differential privacy in policy optimization adds sample complexity costs that often appear as lower-order terms rather than dominating the bounds.
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.
-
On the Sample Complexity of Differentially Private Policy Optimization
Differential privacy in policy optimization adds sample complexity costs that often appear as lower-order terms rather than dominating the bounds.