Excess Risk Bounds for the Bayes Risk using Variational Inference in Latent Gaussian Models
–Neural Information Processing Systems
We strengthen previous results for variational algorithms by showing that they are competitive with any point-estimate predictor. Unlike previous work, we provide bounds on the risk of the Bayesian predictor and not just the risk of the Gibbs predictor for the same approximate posterior.
Neural Information Processing Systems
Nov-21-2025, 11:22:37 GMT
- Country:
- North America > United States
- Massachusetts > Middlesex County
- Medford (0.04)
- California > Los Angeles County
- Long Beach (0.04)
- Massachusetts > Middlesex County
- Europe > United Kingdom
- England
- Cambridgeshire > Cambridge (0.04)
- Oxfordshire > Oxford (0.04)
- England
- Asia > Middle East
- Jordan (0.04)
- North America > United States
- Genre:
- Research Report > New Finding (0.69)
- Technology: