DeepAI AI Chat
Log In Sign Up

On loss functions and regret bounds for multi-category classification

by   Zhiqiang Tan, et al.

We develop new approaches in multi-class settings for constructing proper scoring rules and hinge-like losses and establishing corresponding regret bounds with respect to the zero-one or cost-weighted classification loss. Our construction of losses involves deriving new inverse mappings from a concave generalized entropy to a loss through the use of a convex dissimilarity function related to the multi-distribution f-divergence. We identify new classes of multi-class proper scoring rules, which recover and reveal interesting relationships between various composite losses currently in use. We also derive new hinge-like convex losses, which are tighter convex extensions than related hinge-like losses and geometrically simpler with fewer non-differentiable edges, while achieving similar regret bounds. Finally, we establish new classification regret bounds in general for multi-class proper scoring rules by exploiting the Bregman divergences of the associated generalized entropies, and, as applications, provide simple meaningful regret bounds for two specific classes of proper scoring rules.


page 1

page 2

page 3

page 4


Exp-Concavity of Proper Composite Losses

The goal of online prediction with expert advice is to find a decision s...

Composite Binary Losses

We study losses for binary classification and class probability estimati...

Scoring rules in survival analysis

Scoring rules promote rational and good decision making and predictions ...

Refinement revisited with connections to Bayes error, conditional entropy and calibrated classifiers

The concept of refinement from probability elicitation is considered for...

Surrogate Regret Bounds for Bipartite Ranking via Strongly Proper Losses

The problem of bipartite ranking, where instances are labeled positive o...

Proper losses for discrete generative models

We initiate the study of proper losses for evaluating generative models ...

Non-exponentially weighted aggregation: regret bounds for unbounded loss functions

We tackle the problem of online optimization with a general, possibly un...