Predicting a binary sequence almost as well as the optimal biased coin
COLT '96 Proceedings of the ninth annual conference on Computational learning theory
A randomized approximation of the MDL for stochastic models with hidden variables
COLT '96 Proceedings of the ninth annual conference on Computational learning theory
Analysis of two gradient-based algorithms for on-line regression
COLT '97 Proceedings of the tenth annual conference on Computational learning theory
Distributed cooperative Bayesian learning strategies
COLT '97 Proceedings of the tenth annual conference on Computational learning theory
Minimax relative loss analysis for sequential prediction algorithms using parametric hypotheses
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
The robustness of the p-norm algorithms
COLT '99 Proceedings of the twelfth 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
Viewing all models as “probabilistic”
COLT '99 Proceedings of the twelfth annual conference on Computational learning theory
Text classification using ESC-based stochastic decision lists
Proceedings of the eighth international conference on Information and knowledge management
Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining
Mining from open answers in questionnaire data
Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining
Worst-Case Bounds for the Logarithmic Loss of Predictors
Machine Learning
Algebraic geometrical methods for hierarchical learning machines
Neural Networks
Mining Open Answers in Questionnaire Data
IEEE Intelligent Systems
Text classification using ESC-based stochastic decision lists
Information Processing and Management: an International Journal
Extended Stochastic Complexity and Minimax Relative Loss Analysis
ALT '99 Proceedings of the 10th International Conference on Algorithmic Learning Theory
The Last-Step Minimax Algorithm
ALT '00 Proceedings of the 11th International Conference on Algorithmic Learning Theory
On-Line Estimation of Hidden Markov Model Parameters
DS '00 Proceedings of the Third International Conference on Discovery Science
Mining product reputations on the Web
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
Predicting a binary sequence almost as well as the optimal biased coin
Information and Computation
The subspace information criterion for infinite dimensional hypothesis spaces
The Journal of Machine Learning Research
The Robustness of the p-Norm Algorithms
Machine Learning
Optimality of universal Bayesian sequence prediction for general loss and alphabet
The Journal of Machine Learning Research
Tracking dynamics of topic trends using a finite mixture model
Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
Key semantics extraction by dependency tree mining
Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining
Subspace Information Criterion for Model Selection
Neural Computation
Algebraic Analysis for Nonidentifiable Learning Machines
Neural Computation
A lower bound on compression of unknown alphabets
Theoretical Computer Science
The Journal of Machine Learning Research
Relative loss bounds for on-line density estimation with the exponential family of distributions
UAI'99 Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence
Hi-index | 754.84 |
Rissanen (1978) has introduced stochastic complexity to define the amount of information in a given data sequence relative to a given hypothesis class of probability densities, where the information is measured in terms of the logarithmic loss associated with universal data compression. This paper introduces the notion of extended stochastic complexity (ESC) and demonstrates its effectiveness in design and analysis of learning algorithms in on-line prediction and batch-learning scenarios. ESC can be thought of as an extension of Rissanen's stochastic complexity to the decision-theoretic setting where a general real-valued function is used as a hypothesis and a general loss function is used as a distortion measure. As an application of ESC to on-line prediction, this paper shows that a sequential realization of ESC produces an on-line prediction algorithm called Vovk's aggregating strategy, which can be thought of as an extension of the Bayes algorithm. We derive upper bounds on the cumulative loss for the aggregating strategy both of an expected form and a worst case form in the case where the hypothesis class is continuous. As an application of ESC to batch-learning, this paper shows that a batch-approximation of ESC induces a batch-learning algorithm called the minimum L-complexity algorithm (MLC), which is an extension of the minimum description length (MDL) principle. We derive upper bounds on the statistical risk for the MLC, which are the least to date. Through the ESC we give a unifying view of the most effective learning algorithms that have been explored in computational learning theory