Henning Petzka, Michael Kamp, Linara Adilova, Mario Boley
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Flatness of the loss curve is conjectured to be connected to the generalization ability of machine learning models, in particular neural networks. While it has been empirically observed that flatness measures consistently correlate strongly with generalization, it is still an open theoretical problem why and under which circumstances flatness is connected to generalization, in particular in light of reparameterizations that change certain flatness measures but leave generalization unchanged. We investigate the connection between flatness and generalization by relating it to the interpolation from representative data, deriving notions of representativeness, and feature robustness. The notions allow us to rigorously connect flatness and generalization and to identify conditions under which the connection holds. Moreover, they give rise to a novel, but natural relative flatness measure that correlates strongly with generalization, simplifies to ridge regression for ordinary least squares, and solves the reparameterization issue. * equal contribution Preprint. Under review.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2001.00939")
get_code_for_paper("2001.00939")
have("2001.00939")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2001.00939.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2001.00939)
Connect an agent — have() is free.