Corpus ID: 34179195

Adaptive Sampling for Clustered Ranking

  title={Adaptive Sampling for Clustered Ranking},
  author={S. Katariya and Lalit Jain and Nandana Sengupta and James Evans and R. Nowak},
We consider the problem of sequential or active clustered ranking, where the goal is to sort items according to their means into clusters of pre-specified sizes, by adaptively sampling from their reward distributions. This setting is useful in many social science applications, where an approximate rank of every item is desired. In contrast, a complete ranking of the items requires a large number of samples if the means are close, while only finding the top few items as is done in recommender… Expand

Figures from this paper


Efficient Ranking from Pairwise Comparisons
  • 167
  • PDF
Active Ranking from Pairwise Comparisons and the Futility of Parametric Assumptions
  • 9
  • Highly Influential
  • PDF
An Active Learning Algorithm for Ranking from Pairwise Preferences with an Almost Optimal Query Complexity
  • Nir Ailon
  • Computer Science, Mathematics
  • J. Mach. Learn. Res.
  • 2012
  • 78
  • PDF
Just Sort It! A Simple and Effective Approach to Active Preference Learning
  • 22
  • Highly Influential
  • PDF
Iterative ranking from pair-wise comparisons
  • 202
  • PDF
A Statistical Convergence Perspective of Algorithms for Rank Aggregation from Pairwise Data
  • 115
  • PDF
Rank Centrality: Ranking from Pairwise Comparisons
  • 121
  • PDF
Learning with Limited Rounds of Adaptivity: Coin Tossing, Multi-Armed Bandits, and Ranking from Pairwise Comparisons
  • 48
  • PDF
Active Ranking using Pairwise Comparisons
  • 177
  • PDF