Divide and Couple: Using Monte Carlo Variational Objectives for Posterior Approximation Justin Domke 1 and Daniel Sheldon 1, 2
–Neural Information Processing Systems
Recent work in variational inference (VI) uses ideas from Monte Carlo estimation to tighten the lower bounds on the log-likelihood that are used as objectives.
Neural Information Processing Systems
Oct-3-2025, 02:57:05 GMT
- Country:
- Asia > Middle East
- Jordan (0.04)
- Europe > Sweden
- Östergötland County > Linköping (0.04)
- North America
- Canada > Ontario
- Toronto (0.04)
- United States
- Massachusetts > Hampshire County
- Amherst (0.04)
- New Jersey > Hudson County
- Hoboken (0.04)
- Massachusetts > Hampshire County
- Canada > Ontario
- Asia > Middle East
- Technology: