A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf
.
Extended Stochastic Complexity and Minimax Relative Loss Analysis
[chapter]
1999
Lecture Notes in Computer Science
We are concerned with the problem of sequential prediction using a given hypothesis class of continuously-many prediction strategies. An eective performance measure is the minimax relative cumulative loss (RCL), which is the minimum of the worst-case dierence between the cumulative loss for any prediction algorithm and that for the best assignment in a given hypothesis class. The purpose of this paper is to evaluate the minimax RCL for general continuous hypothesis classes under general losses.
doi:10.1007/3-540-46769-6_3
fatcat:bn7t5e36uvh4tnj233anr2khgm