3 papers
stat.ML2026
Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
Naïl B. Khelifa, Richard E. Turner, Ramji Venkataramanan
Score-based diffusion models are typically trained by minimizing the score matching error, and standard theoretical analyses rely on this quantity to bound the sampling discr…
stat.ML2026
Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization
Naïl B. Khelifa, Richard E. Turner, Ramji Venkataramanan
Recursive training of generative models on their own outputs can lead to model collapse, a compounding drift away from the true data distribution. Existing theoretical works bound…
eess.IV2025
Enhanced Denoising and Convergent Regularisation Using Tweedie Scaling
Naïl Khelifa, Ferdia Sherry, Carola-Bibiane Schönlieb
The inherent ill-posed nature of image reconstruction problems, due to limitations in the physical acquisition process, is typically addressed by introducing a regularisation term…