On large batch training and sharp minima: a Fokker-Planck perspective (Q828491): Difference between revisions

@@ Property / OpenAlex ID @@
+W3043999652
@@ Property / OpenAlex ID: W3043999652 / rank @@
+Normal rank
@@ Property / arXiv ID @@
+.00987
@@ Property / arXiv ID: 2112.00987 / rank @@
+Normal rank
@@ Property / cites work @@
+Stochastic modified equations for the asynchronous stochastic gradient descent
+Normal rank
@@ Property / cites work @@
+Kramers' law: Validity, derivations and generalisations
+Normal rank
@@ Property / cites work @@
+Optimization Methods for Large-Scale Machine Learning
+Normal rank
@@ Property / cites work @@
+Metastability in reversible diffusion processes. I: Sharp asymptotics for capacities and exit times
+Normal rank
@@ Property / cites work @@
+Metastability in reversible diffusion processes. II: Precise asymptotics for small eigenvalues
+Normal rank
@@ Property / cites work @@
+Deep relaxation: partial differential equations for optimizing deep neural networks
+Normal rank
@@ Property / cites work @@
+Q5189317
@@ Property / cites work: Q5189317 / rank @@
+Normal rank
@@ Property / cites work @@
+Q4279615
@@ Property / cites work: Q4279615 / rank @@
+Normal rank
@@ Property / cites work @@
+Q4637063
@@ Property / cites work: Q4637063 / rank @@
+Normal rank
@@ Property / cites work @@
+Stochastic Processes and Applications
@@ Property / cites work: Stochastic Processes and Applications / rank @@
+Normal rank
@@ Property / cites work @@
+Hypocoercivity
@@ Property / cites work: Hypocoercivity / rank @@
+Normal rank