Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs

Timur Garipov, Pavel Izmailov, Dmitrii Podoprikhin, Dmitry P. Vetrov, Andrew G. Wilson

Feb-14-2026, 09:40:14 GMT–Neural Information Processing Systems

The loss functions of deep neural networks are complex and their geometric properties are not well understood.

artificial intelligence, machine learning, procedure, (19 more...)

Neural Information Processing Systems

Feb-14-2026, 09:40:14 GMT

Conferences PDF

Country:
- Europe > Sweden
  - Stockholm > Stockholm (0.04)
- North America > Canada
  - Quebec > Montreal (0.04)
- Oceania > Australia
  - New South Wales > Sydney (0.04)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.35)

Duplicate Docs Excel Report

Title
Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs
Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs

Similar Docs Excel Report more

Title	Similarity	Source
None found