Loss Curvature as a Sampling-Free Proxy for Memorization in Diffusion Models

arXiv:2610.19042 · cs.LG, cs.AI, stat.ML · Submitted 2026-10-13 · Read on arXiv

cs.LG, cs.AI, stat.ML

Submitted: 2026-10-13

Updated: 2026-10-13

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Diffusion Model — 1× in this paper · explained in 10 episodes
• Diffusion Models — 1× in this paper · explained in 9 episodes

Sources

• Transformer Block Coupling and its Correlation with Generalization in LLMs
• Losing dimensions: Geometric memorization in generative diffusion
• Memorization and Regularization in Generative Diffusion Models
• On Memorization in Diffusion Models
• Adam: A Method for Stochastic Optimization
• Optimistic Rates for Learning with a Smooth Loss

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