# Low-loss connection of weight vectors: distribution-based approaches

arXiv: https://arxiv.org/abs/2008.00741 · HTML: https://mlsanity.com/paper/2008.00741/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2020.

## Built on by (most cited first, 3 of 3)

- [When Are Solutions Connected in Deep Networks?](https://mlsanity.com/paper/2102.09671/) (2021)
- [Spurious Local Minima Are Common for Deep Neural Networks with Piecewise Linear Activations](https://mlsanity.com/paper/2102.13233/) (2021)
- [Manifold Metric: A Loss Landscape Approach for Predicting Model Performance](https://mlsanity.com/paper/2405.15895/) (2024)

## Abstract (arXiv)

Recent research shows that sublevel sets of the loss surfaces of overparameterized networks are connected, exactly or approximately. We describe and compare experimentally a panel of methods used to connect two low-loss points by a low-loss curve on this surface. Our methods vary in accuracy and complexity. Most of our methods are based on "macroscopic" distributional assumptions, and some are insensitive to the detailed properties of the points to be connected. Some methods require a prior training of a "global connection model" which can then be applied to any pair of points. The accuracy of the method generally correlates with its complexity and sensitivity to the endpoint detail.