Competitive On‐line Statistics

@inproceedings{Vovk2001CompetitiveOS,
  title={Competitive On‐line Statistics},
  author={Vladimir Vovk},
  year={2001}
}
A radically new approach to statistical modelling, which combines mathematical techniques of Bayesian statistics with the philosophy of the theory of competitive on-line algorithms, has arisen over the last decade in computer science (to a large degree, under the in uence of Dawid's prequential statistics). In this approach, which we call \competitive on-line statistics", it is not assumed that data are generated by some stochastic mechanism; the bounds derived for the performance of… CONTINUE READING
BETA

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 150 CITATIONS, ESTIMATED 29% COVERAGE

Aggregating Algorithm for prediction of packs

VIEW 12 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Fast rates in statistical and online learning

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Prediction with Expert Advice under Discounted Loss

VIEW 8 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Competing with Gaussian linear experts

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Prediction with expert advice for the Brier game

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

BRIEF: Bayesian Regression of Infinite Expert Forecasters for single and multiple time series prediction

  • 2015 54th IEEE Conference on Decision and Control (CDC)
  • 2015
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Beyond Logarithmic Bounds in Online Learning

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Selective sampling and active learning from single and multiple teachers

  • Journal of Machine Learning Research
  • 2012
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Universal Algorithms for Probability Forecasting

  • International Journal on Artificial Intelligence Tools
  • 2012
VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2000
2019

CITATION STATISTICS

  • 36 Highly Influenced Citations

  • Averaged 9 Citations per year over the last 3 years

  • 36% Increase in citations per year in 2018 over 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 64 REFERENCES

Tracking the best expert

VIEW 23 EXCERPTS
HIGHLY INFLUENTIAL

Universal Forecasting Algorithms

  • Inf. Comput.
  • 1992
VIEW 21 EXCERPTS
HIGHLY INFLUENTIAL

Complexity Approximation Principle

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

General linear relations among di erent types of predic- tive complexity

Yuri Kalnichkan
  • In Proceedings of the 1990 Annual Conference on Algo- rithmic Learning Theory,
  • 1999
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

A Game of Prediction with Expert Advice

  • J. Comput. Syst. Sci.
  • 1998
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Universal Data Compression and Linear Prediction

  • Data Compression Conference
  • 1998
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Universal Portfolio Selection

VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…