6 papers
Logarithmic derivatives of variational and singular stochastic partial differential equations
Ehsan Mirafzali, Frank Proske, Razvan Marinescu
For a stochastic partial differential equation posed on a Gelfand triple and satisfying the fully local monotone conditions of Röckner, Shang and Zhang, we compute the logarithmic…
Score-Based Diffusion Models in Infinite Dimensions: A Malliavin Calculus Perspective
Ehsan Mirafzali, Frank Proske, Daniele Venturi +1
We study score-based diffusion modelling in infinite-dimensional separable Hilbert spaces through Malliavin calculus, extending the analysis of generative models beyond the finite-…
Malliavin Calculus for Score-based Diffusion Models
Ehsan Mirafzali, Utkarsh Gupta, Patrick Wyrod +3
We introduce a new framework based on Malliavin calculus to derive exact analytical expressions for the score function , i.e., the gradient of the log-density a…
A Malliavin calculus approach to score functions in diffusion generative models
Ehsan Mirafzali, Frank Proske, Utkarsh Gupta +2
Score-based diffusion generative models have recently emerged as a powerful tool for modelling complex data distributions. These models aim at learning the score function, which de…
Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise
Enea Monzio Compagnoni, Tianlin Liu, Rustem Islamov +3
Despite the vast empirical evidence supporting the efficacy of adaptive optimization methods in deep learning, their theoretical understanding is far from complete. This work intro…
Unbiased and Sign Compression in Distributed Learning: Comparing Noise Resilience via SDEs
Enea Monzio Compagnoni, Rustem Islamov, Frank Norbert Proske +1
Distributed methods are essential for handling machine learning pipelines comprising large-scale models and datasets. However, their benefits often come at the cost of increased co…