Two new research papers propose advancements in Bayesian deep learning, focusing on improving inference methods for neural networks. The first paper argues that sampling-based inference (SAI) has reached computational parity with optimization methods and should become the standard for uncertainty quantification. The second paper introduces a novel, scalable score-based variational inference method that avoids reparameterized sampling and can handle large-scale networks like Vision Transformers, addressing issues like mode collapsing found in other methods. AI
IMPACT These papers advance core research in Bayesian deep learning, potentially improving uncertainty quantification and enabling more scalable inference for complex models.
RANK_REASON Two academic papers published on arXiv proposing new methods for Bayesian deep learning.
- Bayesian deep learning
- Bayesian neural networks (BNNs)
- ELBO-based VI
- Minhyoung Kim
- sampling-based inference (SAI)
- score-based VI
- uncertainty quantification
- variational inference (VI)
- Vision Transformers
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
