How to use expert advice
From MaRDI portal
Publication:4376978
DOI10.1145/258128.258179zbMath0890.68066OpenAlexW1979675141WikidataQ59538623 ScholiaQ59538623MaRDI QIDQ4376978
Yoav Freund, Robert E. Schapire, David Haussler, Nicolò Cesa-Bianchi, Manfred K. Warmuth, David P. Helmbold
Publication date: 17 February 1998
Published in: Journal of the ACM (Search for Journal in Brave)
Full work available at URL: http://www.acm.org/pubs/contents/journals/jacm/1997-44/
Analysis of algorithms and problem complexity (68Q25) Parallel algorithms in computer science (68W10) Theory of languages and software systems (knowledge-based systems, expert systems, etc.) for artificial intelligence (68T35)
Related Items
Generalization bounds for averaged classifiers, On approximating weighted sums with exponentially many terms, Online forecast combinations of distributions: worst case bounds, Learning correlated equilibria in games with compact sets of strategies, Online learning in online auctions, The best expert versus the smartest algorithm, Improved second-order bounds for prediction with expert advice, COMBINING FORECASTING PROCEDURES: SOME THEORETICAL RESULTS, Fast learning rates in statistical inference through aggregation, On minimaxity of follow the leader strategy in the stochastic setting, Competitive On-line Statistics, Asymptotically optimal strategies for online prediction with history-dependent experts, Adaptive regularization of weight vectors, Combining initial segments of lists, Handling concept drift via model reuse, Online Prediction with <scp>History‐Dependent</scp> Experts: The General Case, Optimal anytime regret with two experts, Regret minimization in online Bayesian persuasion: handling adversarial receiver's types under full and partial feedback models, Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback, Unnamed Item, Unnamed Item, User-friendly Introduction to PAC-Bayes Bounds, Universal regression with adversarial responses, Metalearning of time series: an approximate dynamic programming approach, Playing against no-regret players, Synthetic learner: model-free inference on treatments over time, Chasing Ghosts: Competing with Stateful Policies, Scale-free online learning, Sparse regression learning by aggregation and Langevin Monte-Carlo, Learning with stochastic inputs and adversarial outputs, Step decision rules for multistage stochastic programming: a heuristic approach, Regret bounds for sleeping experts and bandits, Finite-time 4-expert prediction problem, Fano's inequality for random variables, Loss functions, complexities, and the Legendre transformation., PORTFOLIO SELECTION AND ONLINE LEARNING, Analysis of two gradient-based algorithms for on-line regression, Randomized prediction of individual sequences, Perfect strategies for the Ulam-Rényi game with multi-interval questions, Linear programming with online learning, Automated trading with boosting and expert weighting, A continuous-time approach to online optimization, The weak aggregating algorithm and weak mixability, Note on universal conditional consistency, Sequential model aggregation for production forecasting, Predicting nearly as well as the best pruning of a decision tree through dynamic programming scheme, Committee, expert advice, and the weighted majority algorithm: an application to the pricing decision of a monopolist, Learning with continuous experts using drifting games, Predictive complexity and information, Prediction and dimension, A quasi-Bayesian perspective to online clustering, General linear relations between different types of predictive complexity, On the multi-interval Ulam-Rényi game: for 3 lies 4 intervals suffice, On Martingale Extensions of Vapnik–Chervonenkis Theory with Applications to Online Learning, Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity, Sensor networks: from dependence analysis via matroid bases to online synthesis, Unnamed Item, A game of prediction with expert advice, Adaptive game playing using multiplicative weights, On Minimaxity of Follow the Leader Strategy in the Stochastic Setting, Scale-Free Algorithms for Online Linear Optimization, Online Learning over a Finite Action Set with Limited Switching, How many strings are easy to predict?, Unnamed Item, Minmax regret solutions for minimax optimization problems with uncertainty, Predicting nearly as well as the best pruning of a planar decision graph., Order-disorder phase transition in heterogeneous populations of self-propelled particles, Suboptimal measures of predictive complexity for absolute loss function, On complexity of easy predictable sequences, Adaptive and self-confident on-line learning algorithms
