Our code is available at https://github.com/sail-sg/stde

First-order optimization methods are a foundational tool in machine learning.

When training complex neural networks, memory usage can be an important bottleneck.

Neural Information Processing Systems http://nips.cc/

Deep neural networks are notorious for being sensitive to small well-chosen perturbations, and estimating the regularity of such architectures is of utmost importance for safe and robust practical applications. In this paper, we investigate one of the key characteristics to assess the regularity of such methods: the Lipschitz constant of deep learning architectures.

The solution in [5,4]requires aone-pass forward computation of marginal probabilities.

Neural Information Processing Systems http://nips.cc/