Escaping Iterative Parameter-Space Noise: Differentially Private Learning with a Hypernetwork
Naoki Nishikawa, Shokichi Takakura, Satoshi Hasegawa
cs.LG, stat.ML
Submitted: 2026-06-25
Code: https://github.com/openai/improved-diffusion
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Conditional LoRA Parameter Generation
- Learning to Learn with Generative Models of Neural Network Checkpoints
- Neural Network Diffusion
- Membership Inference Attacks Against Text-to-image Generation Models
- Differentially Private Subspace Fine-Tuning for Large Language Models
- Private Stochastic Non-Convex Optimization: Adaptive Algorithms and Tighter Generalization Bounds
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks