Abstract | ||
---|---|---|
We consider deep linear networks with arbitrary differentiable loss. We provide a short and elementary proof of the following fact: all local minima are global minima if each hidden layer is wider than either the input or output layer. |
Year | Venue | Field |
---|---|---|
2018 | international conference on machine learning | Topology,Mathematical optimization,Elementary proof,Maxima and minima,Differentiable function,Artificial neural network,Mathematics |
DocType | Citations | PageRank |
Conference | 10 | 0.53 |
References | Authors | |
4 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Laurent, Thomas | 1 | 74 | 7.43 |
James H. von Brecht | 2 | 93 | 6.45 |