Papers › Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling

Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling

25 Feb 2021arXiv:2102.13042archive 2025-07-28

Gregory W. Benton, Wesley J. Maddox, Sanae Lotfi, Andrew Gordon Wilson

With a better understanding of the loss surfaces for multilayer networks, we can build more robust and accurate training procedures. Recently it was discovered that independently trained SGD solutions can be connected along one-dimensional paths of near-constant training loss. In this paper, we show that there are mode-connecting simplicial complexes that form multi-dimensional manifolds of low loss, connecting many independently trained models. Inspired by this discovery, we show how to efficiently build simplicial complexes for fast ensembling, outperforming independently trained deep ensembles in accuracy, calibration, and robustness to dataset shift. Notably, our approach only requires a few training epochs to discover a low-loss simplex, starting from a pre-trained solution. Code is available at https://github.com/g-benton/loss-surface-simplexes.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

g-benton/loss-surface-simplexes officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Deep EnsemblesSGD

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections