SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient
Aaron Mishkin, Frederik Kunstner, Didrik Nielsen, Mark Schmidt, Mohammad Emtiyaz Khan
–Neural Information Processing Systems
To address this issue, we propose a new stochastic, low-rank, approximate natural-gradient (SLANG) method for variational inference in large, deep models. Our method estimates a "diagonal
Neural Information Processing Systems
Nov-20-2025, 20:18:14 GMT
- Country:
- Asia > Japan
- Honshū > Kantō > Tokyo Metropolis Prefecture > Tokyo (0.14)
- Europe
- Switzerland > Vaud
- Lausanne (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Switzerland > Vaud
- North America > Canada
- British Columbia (0.04)
- Quebec > Montreal (0.04)
- Asia > Japan
- Genre:
- Research Report (0.31)
- Industry:
- Health & Medicine (0.69)
- Technology: