3 papers
cs.LG2025
A Bootstrap Perspective on Stochastic Gradient Descent
Hongjian Lan, Yucong Liu, Florian Schäfer
Machine learning models trained with \emph{stochastic} gradient descent (SGD) can generalize better than those trained with deterministic gradient descent (GD). In this work, we st…
math.NA2025
Maximum likelihood discretization of the transport equation
Brook Eyob, Florian Schäfer
The transport of positive quantities underlies countless physical processes, including fluid, gas, and plasma dynamics. Discretizing the associated partial differential equations w…
math.NA2025
Optimal Krylov On Average
Qi Luo, Florian Schäfer
We propose an adaptive randomized truncation estimator for Krylov subspace methods that optimizes the trade-off between the solution variance and the computational cost, while rema…