Matteo Santacesaria — accepted AI-conference papers

2026

MAD: Manifold Attracted Diffusion

Dennis Elbrächter, Giovanni S. Alberti, Matteo Santacesaria

ICML 2026poster

Score-based diffusion models are a highly effective method for generating samples from a distribution of images. We consider scenarios where the training data comes from a noisy version of the target distribution, and present an efficiently implementable modification of the inference procedure to ge…

Cited by 0 Source ↗Scholar ↗

2021

Learning the optimal Tikhonov regularizer for inverse problems

Giovanni S Alberti, Ernesto De Vito, Matti Lassas, Luca Ratti, Matteo Santacesaria

NeurIPS 2021poster

In this work, we consider the linear inverse problem $y=Ax+\varepsilon$, where $A\colon X\to Y$ is a known linear operator between the separable Hilbert spaces $X$ and $Y$, $x$ is a random variable in $X$ and $\epsilon$ is a zero-mean random process in $Y$. This setting covers several inverse proble…

Cited by 48 Source ↗PDF ↗code ↗Scholar ↗