AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Combining Generative and Discriminative Models for Hybrid Inference

Victor Garcia Satorras, Zeynep Akata, Max Welling

NeurIPS 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Latent variable marginalization and estimators

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add learned GNN correction to graphical-model messages (Hybrid vs GM-messages) (ablation)Kalman/HMM graphical inference · Michigan NCLTMSE: 3.0048 -> 1.4109Improved
Add graphical-model messages to GNN (Hybrid vs GNN-messages) (ablation)Gated GNN · Michigan NCLTMSE: 1.7929 -> 1.4109Improved
Replace Kalman Smoother with Hybrid modelKalman Smoother · Michigan NCLTMSE: 3.0099 -> 1.4109Improved
Kalman Smoother vs raw GPS observationsKalman Smoother · Michigan NCLTMSE: 3.4974 -> 3.0099Improved
Use Taylor expansion J=1 prior knowledge in hybrid instead of fully learned GNN (J=0) (ablation)Hybrid model · Lorenz attractorsamples needed for MSE=0.1: 5.000 -> 500Improved
Use Taylor expansion J=1 prior knowledge in hybrid instead of GNN (J=0) (ablation)Hybrid model · Lorenz attractorsamples needed for MSE=0.05: 90.000 -> 5.000Improved
Increase Taylor terms from J=1 to J=2 or 5 (ablation)Hybrid model · Lorenz attractorsamples needed for MSE=0.1: 500 -> 400Improved
Increase Taylor terms from J=1 to J=2 or 5 (ablation)Hybrid model · Lorenz attractorsamples needed for MSE=0.05: 5.000 -> 4.000Improved
Increase Taylor terms J beyond 5 (ablation)Hybrid model · Lorenz attractorMSENo clear effect
Add graphical-model messages to GNN (Hybrid vs GNN) on linear dynamics (ablation)GNN-messages · Linear dynamics syntheticMSEImproved
Hybrid vs Kalman Smoother with more than 1K training samplesKalman Smoother · Linear dynamics syntheticMSEImproved
Use Kalman Smoother vs GNN at low data (<10K) vs high data (>10K)Kalman Smoother vs GNN · Linear dynamics syntheticMSEMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy