Competitive On-line Statistics
From MaRDI portal
Publication:4831997
DOI10.1111/j.1751-5823.2001.tb00457.xzbMath1211.62200OpenAlexW4375906137MaRDI QIDQ4831997
Publication date: 3 January 2005
Published in: International Statistical Review (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1111/j.1751-5823.2001.tb00457.x
Related Items
Dynamic cyber risk estimation with competitive quantile autoregression ⋮ Applications of regularized least squares to pattern classification ⋮ Using the Bayesian Shtarkov solution for predictions ⋮ Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning ⋮ Adaptive and optimal online linear regression on \(\ell^1\)-balls ⋮ Weak aggregating algorithm for the distribution-free perishable inventory problem ⋮ Recursive ridge regression using second-order stochastic algorithms ⋮ Learning noisy linear classifiers via adaptive and selective sampling ⋮ “Calibeating”: Beating forecasters at their own game ⋮ Online Regression Competitive with Changing Predictors ⋮ Aggregating Algorithm for a Space of Analytic Functions ⋮ Weighted last-step min-max algorithm with improved sub-logarithmic regret ⋮ Kernelization of matrix updates, when and how? ⋮ Randomized prediction of individual sequences ⋮ A generalized online mirror descent with applications to classification and regression ⋮ Unnamed Item ⋮ Learning by mirror averaging ⋮ Smooth calibration, leaky forecasts, finite recall, and Nash dynamics ⋮ Online portfolio selection ⋮ Sequential model aggregation for production forecasting ⋮ Unnamed Item ⋮ A quasi-Bayesian perspective to online clustering ⋮ Contextuality of misspecification and data-dependent losses ⋮ Theory and applications of proper scoring rules ⋮ A primal-dual perspective of online learning algorithms ⋮ Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity ⋮ An Upper Bound for Aggregating Algorithm for Regression with Changing Dependencies ⋮ Prediction of Long-Range Dependent Time Series Data with Performance Guarantee ⋮ Aggregating algorithm for prediction of packs ⋮ Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices ⋮ Unnamed Item ⋮ Suboptimality of constrained least squares and improvements via non-linear predictors ⋮ Distribution-free robust linear regression
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Exponentiated gradient versus gradient descent for linear predictors
- Universal forecasting algorithms
- On Bayes methods for on-line Boolean prediction
- A game of prediction with expert advice
- Tracking the best disjunction
- Tracking the best expert
- The weighted majority algorithm
- Jeffreys' prior is asymptotically least favorable under entropy risk
- A decision-theoretic generalization of on-line learning and an application to boosting
- On-line learning and the metrical task system problem
- Adaptive game playing using multiplicative weights
- Universal portfolios with and without transaction costs.
- Derandomizing stochastic prediction strategies
- Probability and Finance
- Present Position and Potential Developments: Some Personal Views: Statistical Theory: The Prequential Approach
- Information-theoretic asymptotics of Bayes methods
- Applied regression analysis bibliography update 1994-97
- Universal Portfolios
- How to use expert advice
- Asymptotic minimax regret for data compression, gambling, and prediction
- Sequential prediction of individual sequences under general loss functions
- Universal portfolios with side information
- Complexity Approximation Principle
- An Information Measure for Classification
- A formal theory of inductive inference. Part I
- Predicting nearly as well as the best pruning of a decision tree through dynamic programming scheme
This page was built for publication: Competitive On-line Statistics
