9 papers
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…
Scaling Laws for Uncertainty in Deep Learning
Mattia Rosso, Simone Rossi, Giulio Franzese +2
Deep learning has recently revealed the existence of scaling laws, demonstrating that model performance follows predictable trends based on dataset and model sizes. Inspired by the…
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…
Repulsive Ensembles for Bayesian Inference in Physics-informed Neural Networks
Philipp Pilar, Markus Heinonen, Niklas Wahlström
Physics-informed neural networks (PINNs) have proven an effective tool for solving differential equations, in particular when considering the inverse problem. When inferring soluti…
Optimizing Data Augmentation through Bayesian Model Selection
Madi Matymov, Ba-Hien Tran, Michael Kampffmeyer +2
Data Augmentation (DA) has become an essential tool to improve robustness and generalization of modern machine learning. However, when deciding on DA strategies it is critical to c…
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…
Robust Classification by Coupling Data Mollification with Label Smoothing
Markus Heinonen, Ba-Hien Tran, Michael Kampffmeyer +1
Introducing training-time augmentations is a key technique to enhance generalization and prepare deep neural networks against test-time corruptions. Inspired by the success of gene…
Improving Discrete Diffusion Models via Structured Preferential Generation
Severi Rissanen, Markus Heinonen, Arno Solin
In the domains of image and audio, diffusion models have shown impressive performance. However, their application to discrete data types, such as language, has often been suboptima…
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…