Active Learning Ranking from Pairwise Preferences with Almost Optimal Query Complexity

نویسنده

  • Nir Ailon
چکیده

Given a set V of n elements we wish to linearly order them using pairwise preference labels which may be non-transitive (due to irrationality or arbitrary noise). The goal is to linearly order the elements while disagreeing with as few pairwise preference labels as possible. Our performance is measured by two parameters: The number of disagreements (loss) and the query complexity (number of pairwise preference labels). Our algorithm adaptively queries at most O(n poly(log n, ε−1)) preference labels for a regret of ε times the optimal loss. This is strictly better, and often significantly better than what non-adaptive sampling could achieve. Our main result helps settle an open problem posed by learning-to-rank (from pairwise information) theoreticians and practitioners: What is a provably correct way to sample preference labels?

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

An Active Learning Algorithm for Ranking from Pairwise Preferences with an Almost Optimal Query Complexity

Given a set V of n elements we wish to linearly order them given pairwise preference labels which may be non-transitive (due to irrationality or arbitrary noise). The goal is to linearly order the elements while disagreeing with as few pairwise preference labels as possible. Our performance is measured by two parameters: The number of disagreements (loss) and the query complexity (number of pai...

متن کامل

Selective Sampling with Almost Optimal Guarantees for Learning to Rank from Pairwise Preferences

One of the practical obstacles of learning to rank from pairwise preference labels is in its (apparent) quadric sample complexity. Some heuristics have been tested for overriding this obstacle. In this workshop we will present new provable method for reducing this sample-complexity, almost reaching the informational lower bound, while suffering only negligible sacrifice of optimality. Our main ...

متن کامل

Learning with Limited Rounds of Adaptivity: Coin Tossing, Multi-Armed Bandits, and Ranking from Pairwise Comparisons

In many learning settings, active/adaptive querying is possible, but the number of rounds of adaptivity is limited. We study the relationship between query complexity and adaptivity in identifying the k most biased coins among a set of n coins with unknown biases. This problem is a common abstraction of many well-studied problems, including the problem of identifying the k best arms in a stocha...

متن کامل

Passive and Active Ranking from Pairwise Comparisons

In the problem of ranking from pairwise comparisons, the learner has access to pairwise preferences among n objects and is expected to output a total order of these objects. This problem has a wide range of applications not only in computer science but also in other areas such as social science and economics. In this report, we will give a survey of passive and active learning algorithms for ra...

متن کامل

Ranking from Stochastic Pairwise Preferences: Recovering Condorcet Winners and Tournament Solution Sets at the Top

We consider the problem of ranking n items from stochastically sampled pairwise preferences. It was shown recently that when the underlying pairwise preferences are acyclic, several algorithms including the Rank Centrality algorithm, the Matrix Borda algorithm, and the SVMRankAggregation algorithm succeed in recovering a ranking that minimizes a global pairwise disagreement error (Rajkumar and ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2011