COLT '90 Proceedings of the third annual workshop on Computational learning theory
The weighted majority algorithm
Information and Computation
Derandomizing Stochastic Prediction Strategies
Machine Learning - Special issue: computational learning theory, COLT '97
Tracking the best linear predictor
The Journal of Machine Learning Research
Universal linear prediction by model order weighting
IEEE Transactions on Signal Processing
Universal Switching Linear Least Squares Prediction
IEEE Transactions on Signal Processing
Coding for a binary independent piecewise-identically-distributed source
IEEE Transactions on Information Theory - Part 2
Low-complexity sequential lossless coding for piecewise-stationary memoryless sources
IEEE Transactions on Information Theory
A zero-delay sequential scheme for lossy coding of individual sequences
IEEE Transactions on Information Theory
IEEE Transactions on Information Theory
Tracking the best level set in a level-crossing analog-to-digital converter
Digital Signal Processing
Online portfolio selection: A survey
ACM Computing Surveys (CSUR)
| Hi-index | 35.69 |
In this paper, we consider a competitive approach to sequential decision problems, suitable for a variety of signal processing applications where at each of a succession of times, a selection must be made from among a fixed set of strategies (or outcomes). For each such decision and outcome pair, loss is incurred, and it is the time-accumulation of these losses that is sought to be minimized. Rather than using a statistical performance measure, our goal in this pursuit is to sequentially accumulate loss that is no larger than that of the best loss that could be obtained through a partitioning of the sequence of observations into an arbitrary fixed number of segments and independently selecting a different strategy for each segment. For this purpose, we introduce a randomized sequential algorithm built upon that of Kozat and Singer that asymptotically achieves the performance of a noncausal algorithm thatwould be able to choose the number of segments and the best algorithm for each segment, based on observing the whole observation process a priori. In addition to improving upon the bounds of Kozat and Singer as well as Gyorgy et al., the results we provide hold formore general loss functions than the square-error loss studied therein.