2025
Amortized Probabilistic Conditioning for Optimization, Simulation and Inference
Paul Edmund Chang, Nasrulloh Ratu Bagus Satrio Loka, Daolang Huang, Ulpu Remes, Samuel Kaski, Luigi Acerbi
AISTATS 2025poster
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 leading models for probabilistic meta-learning with a tractable objective. Often trained on synthetic data, these models…