Algorithms for solving optimization problems arising from deep neural net models: smooth problems

Abstract

Machine Learning models incorporating multiple layered learning networks have been seen to provide effective models for various classification problems. The resulting optimization problem to solve for the optimal vector minimizing the empirical risk is, however, highly nonlinear. This presents a challenge to application and development of appropriate optimization algorithms for solving the problem. In this paper, we summarize the primary challenges involved and present the case for a Newton-based method incorporating directions of negative curvature, including promising numerical results on data arising from security anomally deetection.

References in corpus (2)

• Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods
• Krylov Subspace Descent for Deep Learning

Cited by in corpus (4)

• Gradient-only line searches: An Alternative to Probabilistic Line Searches
• Gradient-only line searches to automatically determine learning rates for a variety of stochastic training algorithms
• GOALS: Gradient-Only Approximations for Line Searches Towards Robust and Consistent Training of Deep Neural Networks
• Traversing the noise of dynamic mini-batch sub-sampled loss functions: A visual guide