On prediction of individual sequences

DOI10.1214/AOS/1017939242zbMATH Open0961.62081OpenAlexW3121527861MaRDI QIDQ1583891FDOQ1583891

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

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

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)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Probability Inequalities for Sums of Bounded Random Variables
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• The weighted majority algorithm
• Weighted sums of certain dependent random variables
• Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension
• Majorizing measures: The generic chaining
• Title not available (Why is that?)
• On the best constants in the Khinchin inequality
• A game of prediction with expert advice
• Universal prediction of individual sequences
• Universal prediction
• Asymptotics via empirical processes. With comments and a rejoinder by the author
• Title not available (Why is that?)
• Empirical processes and applications: An overview. (With discussion)

Cited In (44)

• Universal linear least squares prediction: upper and lower bounds
• High-confidence predictions under adversarial uncertainty
• Asymptotic minimax regret for data compression, gambling, and prediction
• Discrete sequence prediction and its applications
• High-confidence predictions under adversarial uncertainty
• Fast learning rates in statistical inference through aggregation
• Algorithmic Learning Theory
• Online forecast combinations of distributions: worst case bounds
• Learning Theory
• A PDE Approach to the Prediction of a Binary Sequence with Advice from Two History‐Dependent Experts
• Individual Sequence Prediction Using Memory-Efficient Context Trees
• Title not available (Why is that?)
• Blackwell prediction for categorical data
• Internal regret in on-line portfolio selection
• On delayed prediction of individual sequences
• Competing with wild prediction rules
• Improved second-order bounds for prediction with expert advice
• Prediction and tracking of long-range-dependent sequences
• Some Stochastic Properties of Memoryless Individual Sequences
• Sensor networks: from dependence analysis via matroid bases to online synthesis
• Synthetic learner: model-free inference on treatments over time
• Online prediction
• Prediction of stochastic sequences
• Chaining meets chain rule: multilevel entropic regularization and training of neural networks
• Predicting a binary sequence almost as well as the optimal biased coin
• Internal regret in on-line portfolio selection
• Countable alphabet stationary processes with at least one memory word and intermittent estimation with universal rates
• Strategies for Prediction Under Imperfect Monitoring
• Prediction, Learning, and Games
• Randomized prediction of individual sequences
• Minimizing Regret With Label Efficient Prediction
• Sequential Prediction of Unbounded Stationary Time Series
• Some Sufficient Conditions on an Arbitrary Class of Stochastic Processes for the Existence of a Predictor
• Finite-Memory Universal Prediction of Individual Sequences
• Competing with Wild Prediction Rules
• Title not available (Why is that?)
• A simple randomized algorithm for sequential prediction of ergodic time series
• A sharp concentration inequality with applications
• An extension of play against the random past strategy. Choosing the right experts on IBM forecasts
• Universal prediction of individual binary sequences in the presence of noise
• Memoryless sequences for general losses
• Regularization in statistics
• Model selection by bootstrap penalization for classification
• Prediction and dimension

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)