Universal linear least squares prediction: Upper and lower bounds

IEEE Transactions on Information Theory

Volumn 48, Issue 8, 2002, Pages 2354-2362

  Singer, Andrew C ^a,b   Kozat, Suleyman S ^b   Feder, Meir ^a,c  

^a IEEE   (United States)

^b University of Illinois at Urbana Champaign   (United States)

^c TEL AVIV UNIVERSITY   (Israel)

Author keywords

Min max; Prediction; Sequential probability assignment; Universal algorithms

Indexed keywords

SEQUENTIAL PROBABILITY ASSIGNMENT; UNIVERSAL ALGORITHMS;

ALGORITHMS; LEAST SQUARES APPROXIMATIONS; OPTIMIZATION; PROBABILITY; REDUNDANCY;

INFORMATION THEORY;

EID: 0036672580     PISSN: 00189448     EISSN: None     Source Type: Journal    
DOI: 10.1109/TIT.2002.800489     Document Type: Letter

References (14)

1. Competitive on-line statistics
2. Relative loss bounds for on-line density estimation with the exponential family of distributions
3. Universal linear least-squares prediction
4. Competitive on-line linear regression
5. Optimal sequential probability assignment for individual sequences
6. Low complexity sequential lossless coding for piecewise stationary memoryless sources
7. Compression of individual sequences via variable-rate coding
8. Switching between two universal source coding algorithms
9. Universal coding, information, prediction, and estimation
10. The context-tree weighting method: Basic properties
11. Adaptive update algorithms for fixed dictionary lossless data compressors
12. A state-space approach to adaptive RLS filtering
13. Probability, random processes, and estimation theory for engineers
14. Prediction in the worst case