Ranking by calibrated AdaBoost
نویسندگان
چکیده
This paper describes the ideas and methodologies that we used in the Yahoo learning-torank challenge. Our technique is essentially pointwise with a listwise touch at the last combination step. The main ingredients of our approach are 1) preprocessing (querywise normalization) 2) multi-class AdaBoost.MH 3) regression calibration, and 4) an exponentially weighted forecaster for model combination. In post-challenge analysis we found that preprocessing and training AdaBoost with a wide variety of hyperparameters improved individual models significantly, the final listwise ensemble step was crucial, whereas calibration helped only in creating diversity.
منابع مشابه
Margin-based Ranking and an Equivalence between AdaBoost and RankBoost
We study boosting algorithms for learning to rank. We give a general margin-based bound for ranking based on covering numbers for the hypothesis space. Our bound suggests that algorithms that maximize the ranking margin will generalize well. We then describe a new algorithm, smooth margin ranking, that precisely converges to a maximum ranking-margin solution. The algorithm is a modification of ...
متن کاملA Robust Ranking Methodology Based on Diverse Calibration of AdaBoost
In subset ranking, the goal is to learn a ranking function that approximates a gold standard partial ordering of a set of objects (in our case, relevance labels of a set of documents retrieved for the same query). In this paper we introduce a learning to rank approach to subset ranking based on multi-class classification. Our technique can be summarized in three major steps. First, a multi-clas...
متن کاملMargin-Based Ranking Meets Boosting in the Middle
We present a margin-based bound for ranking in a general setting, using the L∞ covering number of the hypothesis space as our complexity measure. Our bound suggests that ranking algorithms that maximize the ranking margin will generalize well. We produce a Smooth Margin Ranking algorithm, which is a modification of RankBoost analogous to Approximate Coordinate Ascent Boosting. We prove that thi...
متن کاملCombining Ordinal Preferences by Boosting
We analyze the relationship between ordinal ranking and binary classification with a new technique called reverse reduction. In particular, we prove that the regret can be transformed between ordinal ranking and binary classification. The proof allows us to establish a general equivalence between the two in terms of hardness. Furthermore, we use the technique to design a novel boosting approach...
متن کاملConditional Models on the Ranking Poset
A distance-based conditional model on the ranking poset is presented for use in classification and ranking. The model is an extension of the Mallows model, and generalizes the classifier combination methods used by several ensemble learning algorithms, including error correcting output codes, discrete AdaBoost, logistic regression and cranking. The algebraic structure of the ranking poset leads...
متن کامل