Amortised Inference: Why Training a Network to Infer Beats Running Optimisation Every Time
Variational inference has a scaling problem. For every new data point, it asks you to solve a fresh optimisation problem: find the approximate posterior that best explains that point. If you have a million data points, you face a million optimisation problems. Amortised inference removes that bottl…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-11-01 14:12 · DEV Community — Machine Learning
Amortised Inference: Why Training a Network to Infer Beats Running Optimisation Every Time