The weighted majority algorithm
From MaRDI portal
Publication:1322487
DOI10.1006/inco.1994.1009zbMath0804.68121WikidataQ29400139 ScholiaQ29400139MaRDI QIDQ1322487
Manfred K. Warmuth, Nicholas Littlestone
Publication date: 1994
Published in: Information and Computation (Search for Journal in Brave)
Full work available at URL: https://semanticscholar.org/paper/35582a30685083c62dca992553eec44123be9d07
68Q25: Analysis of algorithms and problem complexity
68T05: Learning and adaptive systems in artificial intelligence
91B12: Voting theory
Related Items
Competitive On-line Statistics, Multiagent cooperative search for portfolio selection, A general class of adaptive strategies, Probability theory for the Brier game, Predicting nearly as well as the best pruning of a decision tree through dynamic programming scheme, Agnostic learning of geometric patterns, General linear relations between different types of predictive complexity, On-line learning of smooth functions of a single variable, Incremental learning with partial instance memory, Learning recursive functions: A survey, Nonstochastic bandits: Countable decision set, unbounded costs and reactive environments, Consistency of discrete Bayesian learning, Exponential weight algorithm in continuous time, Selection of relevant features and examples in machine learning, Wrappers for feature subset selection, Universal forecasting algorithms, A game of prediction with expert advice, Worst-case analysis of the Perceptron and Exponentiated Update algorithms, The weighted majority algorithm, On-line maximum likelihood prediction with respect to general loss functions, A decision-theoretic generalization of on-line learning and an application to boosting, On the complexity of learning from drifting distributions, Efficient learning with virtual threshold gates, A statistical approach to adaptive problem solving, Predicting a binary sequence almost as well as the optimal biased coin, Loss functions, complexities, and the Legendre transformation., Combining trigram and automatic weight distribution in Chinese spelling error correction, On prediction of individual sequences, Direct and indirect algorithms for on-line learning of disjunctions, Adaptive and self-confident on-line learning algorithms, Regret in the on-line decision problem, Adaptive game playing using multiplicative weights, Conditional universal consistency., On-line learning of linear functions, Predicting nearly as well as the best pruning of a planar decision graph., On learning unions of pattern languages and tree patterns in the mistake bound model., Apple tasting., Suboptimal measures of predictive complexity for absolute loss function, Generalization bounds for averaged classifiers, On approximating weighted sums with exponentially many terms, Online learning in online auctions, Analysis of two gradient-based algorithms for on-line regression, Improved second-order bounds for prediction with expert advice, AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents, Online linear optimization and adaptive routing, How many strings are easy to predict?, Following the Perturbed Leader to Gamble at Multi-armed Bandits, PORTFOLIO SELECTION AND ONLINE LEARNING
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Iterative thresholding for sparse approximations
- Support vector machines with adaptive \(L_q\) penalty
- The weighted majority algorithm
- Large margin classification using the perceptron algorithm
- A sparsity driven kernel machine based on minimizing a generalization error bound
- Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
- Sparse Logistic Regression with Lp Penalty for Biomarker Identification
- Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ 1 minimization
- Nearest neighbor pattern classification