论文信息 - Deep Linear Networks with Arbitrary Loss: All Local Minima Are Global

Deep Linear Networks with Arbitrary Loss: All Local Minima Are Global

We consider deep linear networks with arbitrary convex differentiable loss. We provide a short and elementary proof of the fact that all local minima are global minima if the hidden layers are either 1) at least as wide as the input layer, or 2) at least as wide as the output layer. This result is the strongest possible in the following sense: If the loss is convex and Lipschitz but not differentiable then deep linear networks can have sub-optimal local minima.

Thomas Laurent | James von Brecht | T. Laurent | J. V. Brecht

[1] Haihao Lu,et al. Depth Creates No Bad Local Minima , 2017, ArXiv.

[2] Tengyu Ma,et al. Identity Matters in Deep Learning , 2016, ICLR.

[3] Kenji Kawaguchi,et al. Deep Learning without Poor Local Minima , 2016, NIPS.

[4] Pierre Baldi,et al. Complex-Valued Autoencoders , 2011, Neural Networks.

[5] Surya Ganguli,et al. Exact solutions to the nonlinear dynamics of learning in deep linear neural networks , 2013, ICLR.

[6] Kurt Hornik,et al. Neural networks and principal component analysis: Learning from examples without local minima , 1989, Neural Networks.