REVIEW 2 cited by
Understanding Generalization through Visualizations
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
The power of neural networks lies in their ability to generalize to unseen data, yet the underlying reasons for this phenomenon remain elusive. Numerous rigorous attempts have been made to explain generalization, but available bounds are still quite loose, and analysis does not always lead to true understanding. The goal of this work is to make generalization more intuitive. Using visualization methods, we discuss the mystery of generalization, the geometry of loss landscapes, and how the curse (or, rather, the blessing) of dimensionality causes optimizers to settle into minima that generalize well.
Forward citations
Cited by 2 Pith papers
-
Partitioned integrators for thermodynamic parameterization of neural networks
Layer-partitioned Langevin integrators (LOL and AdLaLa) train single hidden layer perceptrons faster, more accurately, and more robustly than SGD/Adam on hard spiral and trigonometric classification problems.
-
From inverse problems to neural operators: prediction, mechanism, and generalization of data-driven models
Data-driven models for physical systems share a common structure differing only in model class assumptions, with only mechanism-discovering models capable of generalization.
Discussion (0). Continue with ORCID to comment.