Multiclass classification, information, divergence and surrogate risk
نویسندگان
چکیده
منابع مشابه
Multiclass Classification, Information, Divergence, and Surrogate Risk
We provide a unifying view of statistical information measures, multi-class classificationproblems, multi-way Bayesian hypothesis testing, and loss functions, elaborating equivalenceresults between all of these objects. In particular, we consider a particular generalization off -divergences to multiple distributions, and we show that there is a constructive equivalencebetwee...
متن کاملInformation Divergence Measures and Surrogate Loss Functions
In this extended abstract, we provide an overview of our recent work on the connection between information divergence measures and convex surrogate loss functions used in statistical machine learning. Further details can be found in the technical report [7] and conference paper [6]. The class of f -divergences, introduced independently by Csiszar [4] and Ali and Silvey [1], arise in many areas ...
متن کاملConsistency of surrogate risk minimization methods for multiclass 0 - 1 classification
Binary classification Multiclass classification Label space, Y and {±1} [n] Prediction space, T Target 0-1 loss `0-1 : {±1} × {±1} 7→ R+ `0-1 : [n]× [n] 7→ R+ `0-1 : Y × T 7→ R+ `0-1(y, t) = 1(t 6= y) `0-1(y, t) = 1(t 6= y) Surrogate loss ψ : {±1} × C 7→ R+ ψ : [n]× C 7→ R+ ψ : Y × C 7→ R+ where C ⊆ R where C ⊆ R ‘pred’ function pred : C 7→ {±1} pred : C 7→ [n] pred : C 7→ T pred(α) = sign(α) p...
متن کاملCost-sensitive Multiclass Classification Risk Bounds
A commonly used approach to multiclass classification is to replace the 0− 1 loss with a convex surrogate so as to make empirical risk minimization computationally tractable. Previous work has uncovered sufficient and necessary conditions for the consistency of the resulting procedures. In this paper, we strengthen these results by showing how the 0− 1 excess loss of a predictor can be upper bo...
متن کاملAdversarial Multiclass Classification: A Risk Minimization Perspective
Recently proposed adversarial classification methods have shown promising results for cost sensitive and multivariate losses. In contrast with empirical risk minimization (ERM) methods, which use convex surrogate losses to approximate the desired non-convex target loss function, adversarial methods minimize non-convex losses by treating the properties of the training data as being uncertain and...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Annals of Statistics
سال: 2018
ISSN: 0090-5364
DOI: 10.1214/17-aos1657