Large margin optimization of ranking measures
نویسندگان
چکیده
Most ranking algorithms, such as pairwise ranking, are based on the optimization of standard loss functions, but the quality measure to test web page rankers is often different. We present an algorithm which aims at optimizing directly one of the popular measures, the Normalized Discounted Cumulative Gain. It is based on the framework of structured output learning, where in our case the input corresponds to a set of documents and the output is a ranking. The algorithm yields improved accuracies on several public and commercial ranking datasets.
منابع مشابه
Taxonomy of Large Margin Principle Algorithms for Ordinal Regression Problems
We discuss the problem of ranking instances where an instance is associated with an integer from 1 to k. In other words, the specialization of the general multi-class learning problem when there exists an ordering among the instances — a problem known as “ordinal regression” or “ranking learning”. This problem arises in various settings both in visual recognition and other information retrieval...
متن کاملMaximum Margin Ranking Algorithms for Information Retrieval
Machine learning ranking methods are increasingly applied to ranking tasks in information retrieval (IR). However ranking tasks in IR often differ from standard ranking tasks in machine learning, both in terms of problem structure and in terms of the evaluation criteria used to measure performance. Consequently, there has been much interest in recent years in developing ranking algorithms that ...
متن کاملUnsupervised Learning of Discriminative Attributes and Visual Representations — Supplementary Material
l(bi, b + i , b − i ) = max ( 0, ρ+H(bi, b + i ))−H(bi, b − i )) ) , (1) whereH(·, ·) is the Hamming distance between hash codes, ρ is a margin between the Hamming distances of withincluster code pair {bi, b+i } and between-cluster code pair {bi, bi }. The hinge loss is a convex approximation to the 0-1 ranking error, which measures the network’s violation of the ranking order specified in the ...
متن کاملFast Training of Support Vector Machines for Survival Analysis
SV6 = {2, 3, 4, 5, 7, 8} 1.Van Belle et al.: Support Vector Machines for Survival Analysis. In: Proc. 3rd Int. Conf. Comput. Intell. Med. Healthc. 1–8. 2007 2.Lee et al.: Large-Scale Linear RankSVM. Neural Comput. 26(4), 781–817. 2014 3.Chapelle et al.: Efficient algorithms for ranking with SVMs. Information Retrieval 13(3), 201–5. 2009 4.Herbrich et al.: Large Margin Rank Boundaries for Ordina...
متن کاملOptimization for Statistical Machine Translation: A Survey
In statistical machine translation (SMT), the optimization of the system parameters to maximize translation accuracy is now a fundamental part of virtually all modern systems. In this article, we survey 12 years of research on optimization for SMT, from the seminal work on discriminative models (Och and Ney 2002) and minimum error rate training (Och 2003), to the most recent advances. Starting ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2007