202 citations · 638 across the 18 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
stat.ML2019★ 3 cited
Eliminating all bad Local Minima from Loss Landscapes without even adding an Extra Unit
Jascha Sohl-Dickstein, Kenji Kawaguchi
Recent work has noted that all bad local minima can be removed from neural network loss landscapes, by adding a single unit with a particular parameterization. We show that the cor…
cs.LG2019★ 40 cited
Elimination of All Bad Local Minima in Deep Learning
Kenji Kawaguchi, Leslie Pack Kaelbling
In this paper, we theoretically prove that adding one special neuron per output unit eliminates all suboptimal local minima of any deep neural network, for multi-class classificati…