3 citations · 15 across the 36 of their papers we have counts for
3 papers · 1 filter
Implicit Regularization of Large Neural Networks via Mean-Field Formulation
Beatrice Acciaio, Jakob Heiss, Gudmund Pammer +1
We propose a mathematical framework to explain implicit regularization from early stopping during the training of overparametrized neural networks. In the mean-field limit, the par…
Entropic adapted Wasserstein distance on Gaussians
Beatrice Acciaio, Songyan Hou, Gudmund Pammer
The adapted Wasserstein distance is a metric for quantifying distributional uncertainty and assessing the sensitivity of stochastic optimization problems on time series data. A com…
Existence, Duality, and Cyclical monotonicity for weak transport costs
Julio Backhoff Veraguas, Mathias Beiglboeck, Gudmund Pammer
The optimal weak transport problem has recently been introduced by Gozlan et.\ al. We provide general existence and duality results for these problems on arbitrary Polish spaces, a…