Gavin Kerrigan

Postdoc @ Oxford Stats |

[Prof. Anima Anandkumar @AnimaAnandkumar]

Excited to introduce our latest work, Guided Diffusion Sampling on Function Spaces (FunDPS) (https://t.co/O4KUsh62qb) - a discretization-agnostic generative framework for solving PDE-based forward and inverse problems.

Diffusion-based posterior sampling on function spaces: Our model recovers full-field PDE solutions, coefficient functions, and boundary conditions from severely sparse (just 3%) measurements, yielding SotA performance in both speed and accuracy.

Multi-resolution operator learning pipeline: FunDPS leverages Gaussian Random Field priors and neural operator architectures, enabling multi-resolution training and inference, reducing training time by 25% and inference time by 50%.

Infinite-dimensional Tweedie’s Formula: We extend Tweedie’s formula into infinite-dimensional Banach spaces, forming the rigorous theoretical foundation for posterior mean estimation.

Results: Achieved an average 32% accuracy improvement and 4x fewer sampling steps compared to previous SOTA approaches across five challenging PDE tasks. Plus, our multi-resolution inference pipeline accelerates computations by up to 25x!
Paper (https://t.co/O4KUsh62qb). Code (https://t.co/WEspyD8DTJ), based on our earlier workshop paper (https://t.co/RLFGKe9m0P).
@jiacheny7, @AbbasMammadov11, @julberner, @gavinkerrigan, Jong Chul Ye, @Azizzadenesheli
#DiffusionModels #InverseProblems #PDE #MachineLearning #NeuralOperators #AI4Science

[Prakhar Srivastava @SilentBoulevard]

🎉 Excited to share that our paper has been accepted at #NeurIPS2024! We’ve developed a cutting-edge method using video diffusion models to achieve superior precipitation downscaling

📑 Precipitation Downscaling with Spatiotemporal Video Diffusion (https://t.co/4lyDw2Vmqm)

🌧️ Our model captures fine details to ensure reliable ensemble averages, especially for extreme events like heavy rain

👇Thread incoming!

[1/9]

[AISTATS Conference @aistats_conf]

📢AISTATS 2024 is looking for Reviewers and Area Chairs! Self-nominations are welcome! Please sign up here: https://t.co/mg7K7QhFLA. Please share 🔁 and good luck with your NeurIPS rebuttals! 🙂