2 papers
stat.ML2026
Step by Step: Adaptive Gradient Descent for Training L-Lipschitz Neural Networks
Kyle Sung, Kholood Khalil, Noah Forman +2
We demonstrate that applying an eventual decay to the learning rate (LR) in empirical risk minimization (ERM), where the mean-squared-error loss is minimized using standard gradien…
math.PR2025
Counter-example to continuity of measure in uncountable unions
Simranjeet Bilkhu, Noah Mills Forman
Continuity of measure asserts that the measure of the union of an increasing sequence of sets is equal to the supremum of the measures of those sets. We provide counter examples in…