This appendix contains all proofs of the results mentioned in the main body of the paper, plus further results which have been omitted there due to space limits. We recall the following lemma which upper bounds the probability measure of the ball around a point x X that contains its kth nearest neighbors. The proof immediately follows from the multiplicative Chernoff bound (see, e.g., Lemma 3.2 in [28]). When combined with Assumption 5.1 we obtain the following corollary. Corollary A.2. Suppose that the measure-smoothness assumption (Assumption 5.1) holds with parameters λ, Cλ, k k.

Neural Information Processing Systems http://nips.cc/

Converting an n-dimensional vector to a probability distribution over n objects isacommonly used component inmanymachine learning tasks likemulticlass classification,multilabelclassification,attentionmechanismsetc.

We propose in this paper a general framework for deriving loss functions for structured prediction. Inourframework,theuserchooses aconvexsetincluding the output space and provides an oracle forprojectingonto that set.

In modern multilabel classification problems, each data instance belongs to a small number of classes among a large set of classes. In other words, these problems involve learning very sparse binary label vectors. Moreover, in the large-scale problems, the labels typically have certain (unknown) hierarchy. In this paper we exploit the sparsity of label vectors and the hierarchical structure to embed them in low-dimensional space using label groupings. Consequently, we solve the classification problem in a much lower dimensional space and then obtain labels in the original space using an appropriately defined lifting.

Multi-label classification (MLC) has wide practical importance, but the theoretical understanding of its statistical properties is still limited. As an attempt to fill this gap, we thoroughly study upper and lower regret bounds for two canonical MLC performance measures, Hamming loss and Precision@$\kappa$. We consider two different statistical and algorithmic settings, a non-parametric setting tackled by plug-in classifiers \`a la $k$-nearest neighbors, and a parametric one tackled by empirical risk minimization operating on surrogate loss functions. For both, we analyze the interplay between a natural MLC variant of the low noise assumption, widely studied in binary classification, and the label sparsity, the latter being a natural property of large-scale MLC problems. We show that those conditions are crucial in improving the bounds, but the way they are tangled is not obvious, and also different across the two settings.

Neural Information Processing Systems http://nips.cc/

We identify the marginal polytope, the output space's convex hull,

We will correct this inconsistency of terminology.

We present a theoretical analysis of F -measures for binary, multiclass and mul-tilabel classification. These performance measures are non-linear, but in many scenarios they are pseudo-linear functions of the per-class false negative/false positive rate. Based on this observation, we present a general reduction of F - measure maximization to cost-sensitive classification with unknown costs. We then propose an algorithm with provable guarantees to obtain an approximately optimal classifier for the F -measure by solving a series of cost-sensitive classification problems. The strength of our analysis is to be valid on any dataset and any class of classifiers, extending the existing theoretical results on F -measures, which are asymptotic in nature. We present numerical experiments to illustrate the relative importance of cost asymmetry and thresholding when learning linear classifiers on various F -measure optimization tasks.