Optimization and Bayes: A Trade-off for Overparameterized Neural Networks

Feb-9-2026, 11:29:06 GMT–Neural Information Processing Systems

KL divergence between the trained posterior distribution obtained by infinitesimal step size gradient descent and a Gaussian prior.

artificial intelligence, bayesian inference, machine learning, (14 more...)

Neural Information Processing Systems

Feb-9-2026, 11:29:06 GMT

Conferences PDF

Country:
- North America > United States
  - Maryland > Prince George's County > College Park (0.14)
- Europe > United Kingdom
  - England > Cambridgeshire > Cambridge (0.04)
- Asia > Middle East
  - Jordan (0.04)

Technology:
- Information Technology > Artificial Intelligence
  - Representation & Reasoning > Uncertainty
    - Bayesian Inference (0.95)
  - Machine Learning
    - Statistical Learning (1.00)
    - Neural Networks > Deep Learning (0.94)
    - Learning Graphical Models > Directed Networks
      - Bayesian Learning (0.70)

Duplicate Docs Excel Report

Title
2b950a297fc888c95bfeb587ef000d70-Paper-Conference.pdf

Similar Docs Excel Report more

Title	Similarity	Source
None found