2 papers
cs.LG2019
Training Deep Neural Networks by optimizing over nonlocal paths in hyperparameter space
Vlad Pushkarov, Jonathan Efroni, Mykola Maksymenko +1
Hyperparameter optimization is both a practical issue and an interesting theoretical problem in training of deep architectures. Despite many recent advances the most commonly used…
quant-ph2018
Universality of local weak interactions and its application for interferometric alignment
Jan Dziewior, Lukas Knips, Demitry Farfurnik +7
The modification of the effect of interactions of a particle as a function of its pre- and postselected states is analyzed theoretically and experimentally. The universality proper…