1 citations · 2 across the 12 of their papers we have counts for
4 papers · 1 filter
Preferential Normalizing Flows
Petrus Mikkola, Luigi Acerbi, Arto Klami
Eliciting a high-dimensional probability distribution from an expert via noisy judgments is notoriously challenging, yet useful for many applications, such as prior elicitation and…
Amortized Probabilistic Conditioning for Optimization, Simulation and Inference
Paul E. Chang, Nasrulloh Loka, Daolang Huang +3
Amortized meta-learning methods based on pre-training have propelled fields like natural language processing and vision. Transformer-based neural processes and their variants are l…
Amortized Bayesian Workflow
Chengkun Li, Aki Vehtari, Paul-Christian Bürkner +3
Bayesian inference often faces a trade-off between computational speed and sampling accuracy. We propose an adaptive workflow that integrates rapid amortized inference with gold-st…
Improving robustness to corruptions with multiplicative weight perturbations
Trung Trinh, Markus Heinonen, Luigi Acerbi +1
Deep neural networks (DNNs) excel on clean images but struggle with corrupted ones. Incorporating specific corruptions into the data augmentation pipeline can improve robustness to…