131 citations · 172 across the 9 of their papers we have counts for
9 papers
Time Series Diffusion in the Frequency Domain
Jonathan Crabbé, Nicolas Huynh, Jan Stanczuk +1
Fourier analysis has been an instrumental tool in the development of signal processing. This leads us to wonder whether this framework could similarly benefit generative modelling.…
Closing the ODE-SDE gap in score-based diffusion models through the Fokker-Planck equation
Teo Deveney, Jan Stanczuk, Lisa Maria Kreusser +2
Score-based diffusion models have emerged as one of the most promising frameworks for deep generative modelling, due to their state-of-the art performance in many generation tasks…
Variational Diffusion Auto-encoder: Latent Space Extraction from Pre-trained Diffusion Models
Georgios Batzolis, Jan Stanczuk, Carola-Bibiane Schönlieb
As a widely recognized approach to deep generative modeling, Variational Auto-Encoders (VAEs) still face challenges with the quality of generated images, often presenting noticeabl…
Your diffusion model secretly knows the dimension of the data manifold
Jan Stanczuk, Georgios Batzolis, Teo Deveney +1
In this work, we propose a novel framework for estimating the dimension of the data manifold using a trained diffusion model. A diffusion model approximates the score function i.e.…
Navigating the challenges in creating complex data systems: a development philosophy
Sören Dittmer, Michael Roberts, Julian Gilbey +6
In this perspective, we argue that despite the democratization of powerful tools for data science and machine learning over the last decade, developing the code for a trustworthy a…
Non-Uniform Diffusion Models
Georgios Batzolis, Jan Stanczuk, Carola-Bibiane Schönlieb +1
Diffusion models have emerged as one of the most promising frameworks for deep generative modeling. In this work, we explore the potential of non-uniform diffusion models. We show…
Classification of datasets with imputed missing values: does imputation quality matter?
Tolou Shadbahr, Michael Roberts, Jan Stanczuk +15
Classifying samples in incomplete datasets is a common aim for machine learning practitioners, but is non-trivial. Missing data is found in most real-world datasets and these missi…
Conditional Image Generation with Score-Based Diffusion Models
Georgios Batzolis, Jan Stanczuk, Carola-Bibiane Schönlieb +1
Score-based diffusion models have emerged as one of the most promising frameworks for deep generative modelling. In this work we conduct a systematic comparison and theoretical ana…
Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)
Jan Stanczuk, Christian Etmann, Lisa Maria Kreusser +1
Wasserstein GANs are based on the idea of minimising the Wasserstein distance between a real and a generated distribution. We provide an in-depth mathematical analysis of differenc…