Technical Program

Paper Detail

Paper:MLSP-L1.5
Session:Pattern Recognition and Classification I
Time:Thursday, May 20, 10:50 - 11:10
Presentation: Lecture
Topic: Machine Learning for Signal Processing: Signal detection, Pattern Recognition and Classification
Title: MIN-MAX OPTIMAL UNIVERSAL PREDICTION WITH SIDE INFORMATION
Authors: Suleyman Kozat; University of Illinois at Urbana-Champaign 
 Andrew C. Singer; University of Illinois at Urbana-Champaign 
Abstract: We consider the problem of sequential prediction of arbitrary real-valued sequences with side information. We first construct a universal algorithm that asymptotically achieves the performance of the best side-information dependent constant predictor, uniformly for all data and side-information sequences. We then extend these results to linear predictors of some fixed order. We derive matching upper and lower bounds, and show that the algorithms are not only universal but they are also optimal such that no sequential algorithm can give better performance for all sequences.
 
           Back


Home -||- Organizing Committee -||- Technical Committee -||- Technical Program -||- Plenaries
Paper Submission -||- Special Sessions -||- ITT -||- Paper Review -||- Exhibits -||- Tutorials
Information -||- Registration -||- Travel Insurance -||- Housing -||- Workshops

©2015 Conference Management Services, Inc. -||- email: webmaster@icassp2004.org -||- Last updated Wednesday, April 07, 2004