MixtureweightsoptimisationforAlpha-Divergence VariationalInference
–Neural Information Processing Systems
The Power Descent, defined for allα = 1, is one such algorithm and we establish in our work the full proof ofits convergence towards the optimal mixture weights whenα < 1.
Neural Information Processing Systems
Feb-7-2026, 20:55:16 GMT
- Country:
- Asia > Middle East
- Jordan (0.04)
- Europe > France (0.04)
- North America > United States
- California > Alameda County > Berkeley (0.04)
- Asia > Middle East
- Technology: