DeepAI AI Chat
Log In Sign Up

An Embedding Framework for the Design and Analysis of Consistent Polyhedral Surrogates

by   Jessie Finocchiaro, et al.

We formalize and study the natural approach of designing convex surrogate loss functions via embeddings, for problems such as classification, ranking, or structured prediction. In this approach, one embeds each of the finitely many predictions (e.g. rankings) as a point in R^d, assigns the original loss values to these points, and "convexifies" the loss in some way to obtain a surrogate. We establish a strong connection between this approach and polyhedral (piecewise-linear convex) surrogate losses: every discrete loss is embedded by some polyhedral loss, and every polyhedral loss embeds some discrete loss. Moreover, an embedding gives rise to a consistent link function as well as linear surrogate regret bounds. Our results are constructive, as we illustrate with several examples. In particular, our framework gives succinct proofs of consistency or inconsistency for various polyhedral surrogates in the literature, and for inconsistent surrogates, it further reveals the discrete losses for which these surrogates are consistent. We go on to show additional structure of embeddings, such as the equivalence of embedding and matching Bayes risks, and the equivalence of various notions of non-redudancy. Using these results, we establish that indirect elicitation, a necessary condition for consistency, is also sufficient when working with polyhedral surrogates.


An Embedding Framework for Consistent Polyhedral Surrogates

We formalize and study the natural approach of designing convex surrogat...

Towards Consistency in Adversarial Classification

In this paper, we study the problem of consistency in the context of adv...

On the Consistency of AUC Pairwise Optimization

AUC (area under ROC curve) is an important evaluation criterion, which h...

Consistent Polyhedral Surrogates for Top-k Classification and Variants

Top-k classification is a generalization of multiclass classification us...

The Structured Abstain Problem and the Lovász Hinge

The Lovász hinge is a convex surrogate recently proposed for structured ...

A Consistent Regularization Approach for Structured Prediction

We propose and analyze a regularization approach for structured predicti...

Quantifying Learning Guarantees for Convex but Inconsistent Surrogates

We study consistency properties of machine learning methods based on min...