Timezone: »

Adding One Neuron Can Eliminate All Bad Local Minima
SHIYU LIANG · Ruoyu Sun · Jason Lee · R. Srikant

Wed Dec 05 07:45 AM -- 09:45 AM (PST) @ Room 210 #22

One of the main difficulties in analyzing neural networks is the non-convexity of the loss function which may have many bad local minima. In this paper, we study the landscape of neural networks for binary classification tasks. Under mild assumptions, we prove that after adding one special neuron with a skip connection to the output, or one special neuron per layer, every local minimum is a global minimum.

Author Information

Ruoyu Sun (University of Illinois at Urbana-Champaign)
Jason Lee (University of Southern California)
R. Srikant (University of Illinois at Urbana-Champaign)

More from the Same Authors