A game of prediction with expert advice

DOI10.1006/jcss.1997.1556zbMath0945.68528OpenAlexW3149261725MaRDI QIDQ1271549

Vladimir Vovk

Publication date: 27 September 2000

Published in: Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1006/jcss.1997.1556

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (50)

Improved second-order bounds for prediction with expert advice ⋮ Online calibrated forecasts: memory efficiency versus universality for learning in games ⋮ Fast learning rates in statistical inference through aggregation ⋮ A decision-theoretic generalization of on-line learning and an application to boosting ⋮ On minimaxity of follow the leader strategy in the stochastic setting ⋮ Competitive On-line Statistics ⋮ Online Learning with (Multiple) Kernels: A Review ⋮ Combining initial segments of lists ⋮ The Fundamental Nature of the Log Loss Function ⋮ Predicting a binary sequence almost as well as the optimal biased coin ⋮ Relaxing the i.i.d. assumption: adaptively minimax optimal regret via root-entropic regularization ⋮ Online multiple kernel classification ⋮ Scale-free online learning ⋮ Online Regression Competitive with Changing Predictors ⋮ Learning with stochastic inputs and adversarial outputs ⋮ Supermartingales in Prediction with Expert Advice ⋮ Extracting certainty from uncertainty: regret bounded by variation in costs ⋮ Regret bounds for sleeping experts and bandits ⋮ Loss functions, complexities, and the Legendre transformation. ⋮ Finite-sample analysis of \(M\)-estimators using self-concordance ⋮ Analysis of two gradient-based algorithms for on-line regression ⋮ Randomized prediction of individual sequences ⋮ Online aggregation of unbounded losses using shifting experts with confidence ⋮ Unnamed Item ⋮ A continuous-time approach to online optimization ⋮ The weak aggregating algorithm and weak mixability ⋮ A survey on concept drift adaptation ⋮ A lower bound on compression of unknown alphabets ⋮ Probability theory for the Brier game ⋮ Predicting nearly as well as the best pruning of a decision tree through dynamic programming scheme ⋮ Supermartingales in prediction with expert advice ⋮ Predictive complexity and information ⋮ Prediction and dimension ⋮ General linear relations between different types of predictive complexity ⋮ Robust forecast combinations ⋮ Regret to the best vs. regret to the average ⋮ Sensor networks: from dependence analysis via matroid bases to online synthesis ⋮ Unnamed Item ⋮ Adaptive game playing using multiplicative weights ⋮ An Upper Bound for Aggregating Algorithm for Regression with Changing Dependencies ⋮ Prediction with Expert Evaluators’ Advice ⋮ Scale-Free Algorithms for Online Linear Optimization ⋮ Aggregating algorithm for prediction of packs ⋮ On prediction of individual sequences ⋮ Most sequences are stochastic ⋮ Suboptimal measures of predictive complexity for absolute loss function ⋮ On complexity of easy predictable sequences ⋮ Adaptive and self-confident on-line learning algorithms ⋮ Drifting games and Brownian motion ⋮ Does snooping help?

Uses Software

• AdaBoost.MH

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Exponentiated gradient versus gradient descent for linear predictors
• A universal prior for integers and estimation by minimum description length
• Universal forecasting algorithms
• The weighted majority algorithm
• On-line learning of linear functions
• On-line learning with linear loss constraints.
• Prediction in the worst case
• An extension of Borel determinacy
• Present Position and Potential Developments: Some Personal Views: Statistical Theory: The Prequential Approach
• A nonconstructive upper bound on covering radius
• Probability with Martingales
• A Randomization Rule for Selecting Forecasts
• How to use expert advice
• Universal portfolios with side information

This page was built for publication: A game of prediction with expert advice