8 papers
Tightening the Score Matching Gap for Diffusion Models
Benjamin Dupuis, Tyler Farghly, Maxime Haddouche +2
Diffusion models (DMs) are a state-of-the-art generative method to approximately sample from an unknown distribution. Their training and evaluation primarily rely on an Evidence Lo…
Benign Overfitting Does Not Occur in Diffusion Models
Tyler Farghly, Benjamin Dupuis, Alain Durmus +1
Benign overfitting and double descent have come to shape our understanding of generalization in deep learning, establishing that overfitting is not only compatible with good genera…
Metropolis-Adjusted Diffusion Models
Kevin H. Lam, Tyler Farghly, Christopher Williams +3
Sampling from score-based diffusion models incurs bias due to both time discretisation and the approximation of the score function. A common strategy for reducing this bias is to a…
Beyond Real Data: Synthetic Data through the Lens of Regularization
Amitis Shidani, Tyler Farghly, Yang Sun +2
Synthetic data can improve generalization when real data is scarce, but excessive reliance may introduce distributional mismatches that degrade performance. In this paper, we prese…
On-Average Stability of Multipass Preconditioned SGD and Effective Dimension
Simon Vary, Tyler Farghly, Ilja Kuzborskij +1
We study trade-offs between the population risk curvature, geometry of the noise, and preconditioning on the generalisation ability of the multipass Preconditioned Stochastic Gradi…
Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive
Tyler Farghly, Peter Potaptchik, Samuel Howard +2
Diffusion models have achieved state-of-the-art performance, demonstrating remarkable generalisation capabilities across diverse domains. However, the mechanisms underpinning these…