27 citations · 46 across the 11 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.LG2019★ 5 cited
Chameleon: Learning Model Initializations Across Tasks With Different Schemas
Lukas Brinkmeyer, Rafael Rego Drumond, Randolf Scholz +2
Parametric models, and particularly neural networks, require weight initialization as a starting point for gradient-based optimization. Recent work shows that a specific initial pa…
cs.LG2019★ 27 cited
Learning Surrogate Losses
Josif Grabocka, Randolf Scholz, Lars Schmidt-Thieme
The minimization of loss functions is the heart and soul of Machine Learning. In this paper, we propose an off-the-shelf optimization approach that can minimize virtually any non-d…