Pages that link to "Item:Q5073270"
From MaRDI portal
The following pages link to The inverse variance–flatness relation in stochastic gradient descent is critical for finding flat minima (Q5073270):
Displaying 6 items.
- On large batch training and sharp minima: a Fokker-Planck perspective (Q828491) (← links)
- Variance comparison between infinitesimal perturbation analysis and likelihood ratio estimators to stochastic gradient (Q2670503) (← links)
- The effective noise of stochastic gradient descent (Q5043083) (← links)
- Deep networks on toroids: removing symmetries reveals the structure of flat regions in the landscape geometry* (Q5055419) (← links)
- Computation of large-dimension Jordan normal transform via popular platforms (Q6059329) (← links)
- Loss jump during loss switch in solving PDEs with neural networks (Q6646469) (← links)
