Predicting a binary sequence almost as well as the optimal biased coin
COLT '96 Proceedings of the ninth annual conference on Computational learning theory
COLT '96 Proceedings of the ninth annual conference on Computational learning theory
Derandomizing stochastic prediction strategies
COLT '97 Proceedings of the tenth annual conference on Computational learning theory
Universal portfolios with and without transaction costs
COLT '97 Proceedings of the tenth annual conference on Computational learning theory
Competitive solutions for online financial problems
ACM Computing Surveys (CSUR)
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
Minimax regret under log loss for general classes of experts
COLT '99 Proceedings of the twelfth annual conference on Computational learning theory
Designing proxies for stock market indices is computationally hard
Proceedings of the tenth annual ACM-SIAM symposium on Discrete algorithms
Universal Portfolios With and Without Transaction Costs
Machine Learning - Special issue: computational learning theory, COLT '97
Derandomizing Stochastic Prediction Strategies
Machine Learning - Special issue: computational learning theory, COLT '97
Probability theory for the Brier game
Theoretical Computer Science
Predicting nearly as well as the best pruning of a decision tree through dynamic programming scheme
Theoretical Computer Science
Worst-Case Bounds for the Logarithmic Loss of Predictors
Machine Learning
Fast Universalization of Investment Strategies with Provably Good Relative Returns
ICALP '02 Proceedings of the 29th International Colloquium on Automata, Languages and Programming
An additive on-line portfolio selection algorithm
Systems Analysis Modelling Simulation
Predicting a binary sequence almost as well as the optimal biased coin
Information and Computation
Efficient algorithms for universal portfolios
The Journal of Machine Learning Research
Internal Regret in On-Line Portfolio Selection
Machine Learning
Online trading algorithms and robust option pricing
Proceedings of the thirty-eighth annual ACM symposium on Theory of computing
A lower bound on compression of unknown alphabets
Theoretical Computer Science
Log-optimal portfolio models with risk control of VaR and CVaR using genetic algorithms
Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation
Can we learn to beat the best stock
Journal of Artificial Intelligence Research
IEEE Transactions on Signal Processing
Universal simulation with fidelity criteria
IEEE Transactions on Information Theory
Online learning with prior knowledge
COLT'07 Proceedings of the 20th annual conference on Learning theory
IEEE Transactions on Information Theory
Factor graphs for universal portfolios
Asilomar'09 Proceedings of the 43rd Asilomar conference on Signals, systems and computers
Steady-state MSE performance analysis of mixture approaches to adaptive filtering
IEEE Transactions on Signal Processing
CORN: Correlation-driven nonparametric learning approach for portfolio selection
ACM Transactions on Intelligent Systems and Technology (TIST)
Regret minimization algorithms for pricing lookback options
ALT'11 Proceedings of the 22nd international conference on Algorithmic learning theory
Pricing exotic derivatives using regret minimization
SAGT'11 Proceedings of the 4th international conference on Algorithmic game theory
UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence
Trading in markovian price models
COLT'05 Proceedings of the 18th annual conference on Learning Theory
Competitive strategy for on-line leasing of depreciable equipment
Mathematical and Computer Modelling: An International Journal
Confidence Weighted Mean Reversion Strategy for Online Portfolio Selection
ACM Transactions on Knowledge Discovery from Data (TKDD)
ACM Transactions on Computation Theory (TOCT)
Online portfolio selection: A survey
ACM Computing Surveys (CSUR)
| Hi-index | 754.97 |
We present a sequential investment algorithm, the μ-weighted universal portfolio with side information, which achieves, to first order in the exponent, the same wealth as the best side-information dependent investment strategy (the best state-constant rebalanced portfolio) determined in hindsight from observed market and side-information outcomes. This is an individual sequence result which shows the difference between the exponential growth wealth of the best state-constant rebalanced portfolio and the universal portfolio with side information is uniformly less than (d/(2n))log (n+1)+(k/n)log 2 for every stock market and side-information sequence and for all time n. Here d=k(m-1) is the number of degrees of freedom in the state-constant rebalanced portfolio with k states of side information and m stocks. The proof of this result establishes a close connection between universal investment and universal data compression