Prediction, Learning, and Games

From MaRDI portal
Revision as of 02:55, 7 March 2024 by Import240305080351 (talk | contribs) (Created automatically from import240305080351)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Publication:5470194

DOI10.1017/CBO9780511546921zbMath1114.91001WikidataQ59538584 ScholiaQ59538584MaRDI QIDQ5470194

Nicolò Cesa-Bianchi, Gábor Lugosi

Publication date: 30 May 2006





Related Items (only showing first 100 items - show all)

Robust Bregman clusteringRobust option pricing: Hannan and Blackwell meet Black and ScholesRobust probability updatingLower bounds on individual sequence regretOne-pass AUC optimizationOptimal control with learning on the fly: a toy problemApproximation algorithms for stochastic combinatorial optimization problemsA general internal regret-free strategyWoodroofe's one-armed bandit problem revisitedStrategic conversations under imperfect information: epistemic message exchange gamesOnline passive-aggressive active learningSublinear time algorithms for approximate semidefinite programmingConsensus in opinion dynamics as a repeated gameImproving multi-armed bandit algorithms in online pricing settingsBandit online optimization over the permutahedronThe query complexity of correlated equilibriaRobust mean field gamesOnline ordering policies for a two-product, multi-period stationary newsvendor problemUsing the Bayesian Shtarkov solution for predictionsA general procedure to combine estimatorsThe multi-armed bandit problem with covariatesOpen problems in universal induction \& intelligenceOn data-based optimal stopping under stationarity and ergodicityOn minimaxity of follow the leader strategy in the stochastic settingWisdom of crowds versus groupthink: learning in groups and in isolationTwo queues with non-stochastic arrivalsExploration and exploitation of scratch games\(\lambda \)-perceptron: an adaptive classifier for data streamsAdaptive and optimal online linear regression on \(\ell^1\)-ballsWeak aggregating algorithm for the distribution-free perishable inventory problemWeakly universally consistent static forecasting of stationary and ergodic time series via local averaging and least squares estimatesStochastic optimization for real time service capacity allocation under random service demandReducing reinforcement learning to KWIK online regressionMinimax PAC bounds on the sample complexity of reinforcement learning with a generative modelAggregation of predictors for nonstationary sub-linear processes and online adaptive forecasting of time varying autoregressive processesCombining multiple strategies for multiarmed bandit problems and asymptotic optimalityStability in large Bayesian games with heterogeneous playersClassifier evaluation and attribute selection against active adversariesCommon learning with intertemporal dependenceLearning noisy linear classifiers via adaptive and selective samplingSharp oracle inequalities for aggregation of affine estimatorsApproximate implementation in Markovian environmentsOnline variance minimizationPAMR: passive aggressive mean reversion strategy for portfolio selectionOptimization of relative arbitrageRisk management strategies for finding universal portfoliosForecasting electricity consumption by aggregating specialized expertsMercer's theorem on general domains: on the interaction between measures, kernels, and RKHSsQoS commitment between vertically integrated autonomous systemsHow uncertain do we need to be?Scale-free online learningCombinatorial banditsSparse regression learning by aggregation and Langevin Monte-CarloLearning with stochastic inputs and adversarial outputsModel selection for weakly dependent time series forecastingMirror averaging with sparsity priorsGaussian process bandits with adaptive discretizationOnline transfer learningReal-time model learning using incremental sparse spectrum Gaussian process regressionWeighted last-step min-max algorithm with improved sub-logarithmic regretRegret minimization in repeated matrix games with variable stage durationLoad balancing without regret in the bulletin board modelStrong approachabilityRandomized prediction of individual sequencesOnline aggregation of unbounded losses using shifting experts with confidenceEfficient distance metric learning by adaptive sampling and mini-batch stochastic gradient descent (SGD)A generalized online mirror descent with applications to classification and regressionEmergence of information transfer by inductive learningMarkets, correlation, and regret-matchingOnline estimation of discrete, continuous, and conditional joint densities using classifier chainsConsistency of discrete Bayesian learningOn the possibility of learning in reactive environments with arbitrary dependenceLeading strategies in competitive on-line predictionAsymptotic sequential Rademacher complexity of a finite function classLearning by mirror averagingA continuous-time approach to online optimizationSmooth calibration, leaky forecasts, finite recall, and Nash dynamicsSampled fictitious play is Hannan consistentDominant-set clustering: a reviewMSO: a framework for bound-constrained black-box global optimization algorithmsThe weak aggregating algorithm and weak mixabilityNote on universal conditional consistencyCRPS LearningOptimal learning with Bernstein Online AggregationHow long to equilibrium? The communication complexity of uncoupled equilibrium proceduresSupermartingales in prediction with expert adviceWindow-games between TCP flowsContext tree selection: a unifying viewQuantization and clustering with Bregman divergencesA quasi-Bayesian perspective to online clusteringGeneralized mirror averaging and \(D\)-convex aggregationRobust forecast combinationsLogarithmic regret algorithms for online convex optimizationAggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsityRegret to the best vs. regret to the averageOn-line predictive linear regressionA nonmanipulable testMulti-agent learning for engineersOn universal algorithms for adaptive forecastingAn asymptotically optimal strategy for constrained multi-armed bandit problems







This page was built for publication: Prediction, Learning, and Games