7 papers
Softly Constrained Denoisers for Diffusion Models Applied to Partial Differential Equations
Victor M. Yeom-Song, Severi Rissanen, Arno Solin +2
Diffusion models have become a powerful generative prior for solutions of partial differential equations (PDEs). Existing approaches enforce physical constraints either by adding t…
PriorGuide: Test-Time Prior Adaptation for Simulation-Based Inference
Yang Yang, Severi Rissanen, Paul E. Chang +5
Amortized simulator-based inference offers a powerful framework for tackling Bayesian inference in computational fields such as engineering or neuroscience, increasingly leveraging…
Pareto-Conditioned Diffusion Models for Offline Multi-Objective Optimization
Jatan Shrestha, Santeri Heiskanen, Kari Hepola +3
Multi-objective optimization (MOO) arises in many real-world applications where trade-offs between competing objectives must be carefully balanced. In the offline setting, where on…
Progressive Tempering Sampler with Diffusion
Severi Rissanen, RuiKang OuYang, Jiajun He +4
Recent research has focused on designing neural samplers that amortize the process of sampling from unnormalized densities. However, despite significant advancements, they still fa…
Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models
Najwa Laabid, Severi Rissanen, Markus Heinonen +2
Graph diffusion models, dominant in graph generative modeling, remain underexplored for graph-to-graph translation tasks like chemical reaction prediction. We demonstrate that stan…
Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs
Severi Rissanen, Markus Heinonen, Arno Solin
The covariance for clean data given a noisy observation is an important quantity in many training-free guided generation methods for diffusion models. Current methods require heavy…