Fundamentals of speech recognition
Fundamentals of speech recognition
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
A game of prediction with expert advice
Journal of Computer and System Sciences - Special issue on the eighth annual workshop on computational learning theory, July 5–8, 1995
Universal Portfolios With and Without Transaction Costs
Machine Learning - Special issue: computational learning theory, COLT '97
Derandomizing Stochastic Prediction Strategies
Machine Learning - Special issue: computational learning theory, COLT '97
Statistical Language Learning
Efficient algorithms for universal portfolios
FOCS '00 Proceedings of the 41st Annual Symposium on Foundations of Computer Science
Internal Regret in On-Line Portfolio Selection
Machine Learning
Prediction, Learning, and Games
Prediction, Learning, and Games
On-line algorithms for combining language models
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 02
Can we learn to beat the best stock
Journal of Artificial Intelligence Research
IEEE Transactions on Signal Processing
Stochastic correlative learning algorithms
IEEE Transactions on Signal Processing
Testing (non-)existence of input-output relationships by estimating fractal dimensions
IEEE Transactions on Signal Processing
IEEE Transactions on Signal Processing
Universal Switching Linear Least Squares Prediction
IEEE Transactions on Signal Processing
Universal portfolios with side information
IEEE Transactions on Information Theory
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
IEEE Transactions on Signal Processing
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 |
A wide variety of problems in signal processing can be formulated such that decisions are made by sequentially taking convex combinations of vector-valued observations and these convex combinations are then multiplicatively compounded over time. A "universal" approach to such problems might attempt to sequentially achieve the performance of the best fixed convex combination, as might be achievable noncausally, by observing all of the outcomes in advance. By permitting different piecewise-fixed strategies within contiguous regions of time, the best algorithm in this broader class would be able to switch between different fixed strategies to optimize performance to the changing behavior of each individual sequence of outcomes. Without knowledge of the data length or the number of switches necessary, the algorithms developed in this paper can achieve the performance of the best piecewise-fixed strategy that can choose both the partitioning of the sequence of outcomes in time as well as the best strategy within each time segment. We compete with an exponential number of such partitions, using only complexity linear in the data length and demonstrate that the regret with respect to the best such algorithm is at most O(ln(n)) in the exponent, where n is the data length. Finally, we extend these results to include finite collections of candidate algorithms, rather than convex combinations and further investigate the use of an arbitrary side-information sequence.