Simple Risk Bounds for Position-Sensitive Max-Margin Ranking Algorithms
نویسندگان
چکیده
R bounds for position-sensitive max-margin ranking algorithms can be derived straightforwardly from a structural result for Rademacher averages presented by [1]. We apply this result to pairwise and listwise hinge loss that are position-sensitive by virtue of rescaling the margin by a pairwise or listwise position-sensitive prediction loss. Similar bounds have recently been presented for probabilistic listwise ranking algorithms by [2]. More involved risk bounds for pairwise ranking algorithms have been presented before by [3] (using algorithmic stability), and for structured prediction by [4] (using PAC-Bayesian theory).
منابع مشابه
Reduction from Cost-Sensitive Ordinal Ranking to Weighted Binary Classification
We present a reduction framework from ordinal ranking to binary classification. The framework consists of three steps: extracting extended examples from the original examples, learning a binary classifier on the extended examples with any binary classification algorithm, and constructing a ranker from the binary classifier. Based on the framework, we show that a weighted 0/1 loss of the binary ...
متن کاملFrom Ordinal Ranking to Binary Classification
We study the ordinal ranking problem in machine learning. The problem can be viewed as a classification problem with additional ordinal information or as a regression problem without actual numerical information. From the classification perspective, we formalize the concept of ordinal information by a cost-sensitive setup, and propose some novel cost-sensitive classification algorithms. The alg...
متن کاملClassification Algorithms using Adaptive Partitioning
Algorithms for binary classification based on adaptive partitioning are formulated and analyzed for both their risk performance and their friendliness to numerical implementation. The algorithms can be viewed as generating a set approximation to the Bayes set and thus fall into the general category of set estimators. A general theory is developed to analyze the risk performance of set estimator...
متن کاملUpper bounds and aggregation in bipartite ranking
One main focus of learning theory is to find optimal rates of convergence. In classification, it is possible to obtain optimal fast rates (faster than n−1/2) in a minimax sense. Moreover, using an aggregation procedure, the algorithms are adaptive to the parameters of the class of distributions. Here, we investigate this issue in the bipartite ranking framework. We design a ranking rule by aggr...
متن کاملPerceptron-like Algorithms and Generalization Bounds for Learning to Rank
Learning to rank is a supervised learning problem where the output space is the space of rankings but the supervision space is the space of relevance scores. We make theoretical contributions to the learning to rank problem both in the online and batch settings. First, we propose a perceptron-like algorithm for learning a ranking function in an online setting. Our algorithm is an extension of t...
متن کامل