A tree-weighting approach to sequential decision problems with multiplicative loss

DOI10.1016/j.sigpro.2010.09.007zbMath1217.91041MaRDI QIDQ551626

Andrew Bean, Suleyman S. Kozat, Andrew C. Singer

Publication date: 21 July 2011

Published in: Signal Processing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.sigpro.2010.09.007

zbMATH Keywords

portfolio; investment; universal; context-tree; convex-combination; piecewise models

Mathematics Subject Classification ID

91G70: Statistical methods; risk measures

91B06: Decision theory

62C12: Empirical decision procedures; empirical Bayes procedures

Related Items

Online portfolio selection

Cites Work

• Unnamed Item
• Unnamed Item
• Twice-universal coding
• Universal portfolios with and without transaction costs.
• The Cost of Achieving the Best Portfolio in Hindsight
• Coding for a binary independent piecewise-identically-distributed source
• The context-tree weighting method: extensions
• Efficient Universal Portfolios for Past‐Dependent Target Classes
• Universal Piecewise Linear Prediction Via Context Trees
• Switching Strategies for Sequential Decision Problems With Multiplicative Loss With Application to Portfolios
• Low-complexity sequential lossless coding for piecewise-stationary memoryless sources
• On‐Line Portfolio Selection Using Multiplicative Updates
• Multi-stream adaptive evidence combination for noise robust ASR
• 10.1162/153244303321897672
• The context-tree weighting method: basic properties
• Universal portfolios with side information
• Context weighting for general finite-context sources
• Introduction to Digital Speech Processing
• NONPARAMETRIC KERNEL‐BASED SEQUENTIAL INVESTMENT STRATEGIES
• Portfolio Selection with Transaction Costs
• Internal regret in on-line portfolio selection