Beyond Backprop: Online Alternating Minimization with Auxiliary Variables

Anna Choromanska, Benjamin Cowen, Sadhana Kumaravel, Ronny Luss, Mattia Rigotti, Irina Rish, Paolo Diachille, Viatcheslav Gurev, Brian Kingsbury, Ravi Tejwani, Djallel Bouneffouf

Abstract: Despite significant recent advances in deep neural networks, training them remains a challenge due to the highly non-convex nature of the objective function. State-of-the-art methods rely on error ...