Publications
Generative Diffusion Models for Sequential Recommendations
Sharare Zolghadr, Ole Winther, Paul Jeha
RECSYS 24, Workshop on Risks, Opportunities, and Evaluation of Generative Models in Recommender Systems ARXIV
Variance reduction of diffusion model’s gradients with Taylor approximation-based control variate
Paul Jeha, Will Grathwohl, Michael Riis Andersen, Carl Henrik Ek, Jes Frellsen
ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling
Learning energy-based models by self-normalising the likelihood
Hugo Henri Joseph Senetaire, Paul Jeha, Jes Frellsen, Pierre-Alexandre Mattei
Work in progress, 2024
PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series
Paul Jeha*, Michael Bohlke-Schneider*, Pedro Mercado, Shubham Kapoor, Rajbir Singh Nirwan, Valentin Flunkert, Jan Gasthaus, Tim Januschowsk
International Conference on Learning Representations (ICLR) , 2022
ICML Workshop on Time Series, 2021. - Contributed Talk