English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we first present an explanation regarding the commonoccurrence of spikes in the training loss when neural networks are trained withstochastic gradient descent (SGD). We provide evidence that the spikes in thetraining loss of SGD are "catapults", an optimization phenomenon originallyobserved in GD with large learning rates in [Lewkowycz et al. 2020]. Weempirically show that these catapults occur in a low-dimensional subspacespanned by the top eigenvectors of the tangent kernel, for both GD and SGD.Second, we posit an explanation for how catapults lead to better generalizationby demonstrating that catapults promote feature learning by increasingalignment with the Average Gradient Outer Product (AGOP) of the true predictor.Furthermore, we demonstrate that a smaller batch size in SGD induces a largernumber of catapults, thereby improving AGOP alignment and test performance.

Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning