On prediction of individual sequences

DOI10.1214/AOS/1017939242MaRDI QIDQ1583891zbMATH OpenOpenAlexFDO

Authors Nicolò Cesa-Bianchi, Gábor Lugosi

Publication date 5 June 2001

Published in The Annals of Statistics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1214/aos/1017939242

zbMATH Keywords

empirical processescovering numbersfinite-state machinesuniversal predictionprediction with expertsabsolute loss

Mathematics Subject Classification ID

Inference from stochastic processes and prediction (62M20) Prediction theory (aspects of stochastic processes) (60G25)

Recommendations

• A simple randomized algorithm for sequential prediction of ergodic time series
• Prediction, Learning, and Games
• scientific article; zbMATH DE number 1301979
• Predicting a binary sequence almost as well as the optimal biased coin
• Worst-case bounds for the logarithmic loss of predictors

Cites work

• scientific article; zbMATH DE number 4170917 (Why is no real title available?)
• scientific article; zbMATH DE number 3723610 (Why is no real title available?)
• scientific article; zbMATH DE number 49190 (Why is no real title available?)
• scientific article; zbMATH DE number 193528 (Why is no real title available?)
• scientific article; zbMATH DE number 193660 (Why is no real title available?)
• scientific article; zbMATH DE number 1301979 (Why is no real title available?)
• scientific article; zbMATH DE number 3274494 (Why is no real title available?)
• A game of prediction with expert advice
• Asymptotics via empirical processes. With comments and a rejoinder by the author
• Empirical processes and applications: An overview. (With discussion)
• Majorizing measures: The generic chaining
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• On the best constants in the Khinchin inequality
• Probability Inequalities for Sums of Bounded Random Variables
• Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension
• The weighted majority algorithm
• Universal prediction
• Universal prediction of individual sequences
• Weighted sums of certain dependent random variables

Cited in

(44)

• Universal prediction of individual binary sequences in the presence of noise
• Algorithmic Learning Theory
• Randomized prediction of individual sequences
• Prediction, Learning, and Games
• Competing with Wild Prediction Rules
• Minimizing Regret With Label Efficient Prediction
• Sequential Prediction of Unbounded Stationary Time Series
• Finite-Memory Universal Prediction of Individual Sequences
• Internal regret in on-line portfolio selection
• Prediction of stochastic sequences
• Blackwell prediction for categorical data
• Some Sufficient Conditions on an Arbitrary Class of Stochastic Processes for the Existence of a Predictor
• Online forecast combinations of distributions: worst case bounds
• Improved second-order bounds for prediction with expert advice
• Universal linear least squares prediction: upper and lower bounds
• Fast learning rates in statistical inference through aggregation
• Chaining meets chain rule: multilevel entropic regularization and training of neural networks
• High-confidence predictions under adversarial uncertainty
• Some Stochastic Properties of Memoryless Individual Sequences
• Predicting a binary sequence almost as well as the optimal biased coin
• On delayed prediction of individual sequences
• Memoryless sequences for general losses
• Internal regret in on-line portfolio selection
• Sensor networks: from dependence analysis via matroid bases to online synthesis
• Individual Sequence Prediction Using Memory-Efficient Context Trees
• Prediction and dimension
• High-confidence predictions under adversarial uncertainty
• Regularization in statistics
• Synthetic learner: model-free inference on treatments over time
• scientific article; zbMATH DE number 2230439 (Why is no real title available?)
• scientific article; zbMATH DE number 4048837 (Why is no real title available?)
• Online prediction
• Asymptotic minimax regret for data compression, gambling, and prediction
• Prediction and tracking of long-range-dependent sequences
• A simple randomized algorithm for sequential prediction of ergodic time series
• Competing with wild prediction rules
• Discrete sequence prediction and its applications
• Learning Theory
• A sharp concentration inequality with applications
• Countable alphabet stationary processes with at least one memory word and intermittent estimation with universal rates
• Model selection by bootstrap penalization for classification
• Strategies for Prediction Under Imperfect Monitoring
• An extension of play against the random past strategy. Choosing the right experts on IBM forecasts
• A PDE Approach to the Prediction of a Binary Sequence with Advice from Two History‐Dependent Experts

This page was built for publication: On prediction of individual sequences

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1583891)