Non-attracting Regions of Local Minima in Deep and Wide Neural Networks

Abstract

Understanding the loss surface of neural networks is essential for the design of models with predictable performance and their success in applications. Experimental results suggest that sufficiently deep and wide neural networks are not negatively impacted by suboptimal local minima. Despite recent progress, the reason for this outcome is not fully understood. Could deep networks have very few, if at all, suboptimal local optima? or could all of them be equally good? We provide a construction to show that suboptimal local minima (i.e., non-global ones), even though degenerate, exist for fully connected neural networks with sigmoid activation functions. The local minima obtained by our construction belong to a connected set of local solutions that can be escaped from via a non-increasing path on the loss curve. For extremely wide neural networks of decreasing width after the wide layer, we prove that every suboptimal local minimum belongs to such a connected set. This provides a partial explanation for the successful application of deep neural networks. In addition, we also characterize under what conditions the same construction leads to saddle points instead of local minima for deep neural networks.

References in corpus (14)

• Understanding deep learning requires rethinking generalization
• The Loss Surfaces of Multilayer Networks
• Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
• The loss surface of deep and wide neural networks
• The statistics of critical points of Gaussian fields on large-dimensional spaces
• No bad local minima: Data independent training error guarantees for multilayer neural networks
• Mathematics of Deep Learning
• Depth Creates No Bad Local Minima
• On the loss landscape of a class of deep neural networks with no bad local valleys
• Exponentially vanishing sub-optimal local minima in multilayer neural networks
• Optimization Landscape and Expressivity of Deep CNNs
• Understanding the Loss Surface of Neural Networks for Binary Classification
• Adding One Neuron Can Eliminate All Bad Local Minima
• Local minima in training of neural networks

Cited by in corpus (1)

• Optimization Landscapes of Wide Deep Neural Networks Are Benign