Skip to content

Author

Tony Bonnaire

We have 3 of 8 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

First Learn, Then Memorize: The Spectral Bias of Diffusion Models

Analytically, the spectrum is solved in the lazy high-dimensional limit for both linear ($n \asymp d) and polynomial ($n \asymp d^k$) sample complexities, and it is proved through a bias--variance decomposition that the first bulk minimizes the approximation error while the second drives the error associated with memor...

Raphaël Urfin, Tony Bonnaire, Giulio Biroli et al. · 1 citation

Double Descent and Malign Overfitting in Diffusion Models

Overparameterization remains beneficial when paired with regularization: in the random-features theory and in U-Net experiments, optimally regularized large models---via a ridge penalty or early stopping, respectively---outperform any unregularized models.

Raphaël Urfin, Tony Bonnaire, Giulio Biroli et al. · 0 citations
Open access Aug 2026

Why diffusion models do not memorize: the role of implicit dynamical regularization in training

It is found that τmem increases linearly with the training set size n, whereas τgen remains constant, which creates a growing window of training times with n where models generalize effectively, despite showing strong memorization if training continues beyond it.

Tony Bonnaire, Raphaël Urfin, Giulio Biroli et al. · 2 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.