Poster
Equilibrated adaptive learning rates for non-convex optimization
Yann Dauphin · Harm de Vries · Yoshua Bengio

Wed Dec 9th 07:00 -- 11:59 PM @ 210 C #27 #None

Parameter-specific adaptive learning rate methods are computationally efficient ways to reduce the ill-conditioning problems encountered when training large deep networks. Following recent work that strongly suggests that most of thecritical points encountered when training such networks are saddle points, we find how considering the presence of negative eigenvalues of the Hessian could help us design better suited adaptive learning rate schemes. We show that the popular Jacobi preconditioner has undesirable behavior in the presence of both positive and negative curvature, and present theoretical and empirical evidence that the so-called equilibration preconditioner is comparatively better suited to non-convex problems. We introduce a novel adaptive learning rate scheme, called ESGD, based on the equilibration preconditioner. Our experiments demonstrate that both schemes yield very similar step directions but that ESGD sometimes surpasses RMSProp in terms of convergence speed, always clearly improving over plain stochastic gradient descent.

Author Information

Yann Dauphin (Facebook AI Research)
Harm de Vries (Element AI)
Yoshua Bengio (U. Montreal)

More from the Same Authors