On Structured Prediction Theory with Calibrated Convex Surrogate Losses

P. 302–313.

Osokin A., Bach F., Lacoste-Julien S.

We provide novel theoretical insights on structured prediction in the context of efficient convex surrogate loss minimization with consistency guarantees. For any task loss, we construct a convex surrogate that can be optimized via stochastic gradient descent and we prove tight bounds on the so-called "calibration function" relating the excess surrogate risk to the actual risk. In contrast to prior related work, we carefully monitor the effect of the exponential number of classes in the learning guarantees as well as on the optimization complexity. As an interesting consequence, we formalize the intuition that some task losses make learning harder than others, and that the classical 0-1 loss is ill-suited for structured prediction.

Keywords: theory of computation and machine learning, structured prediction, convex optimization

In book

Advances in Neural Information Processing Systems 30 (NIPS 2017)

Montreal: Curran Associates, 2017.