Universal prediction

From MaRDI portal
Publication:4701188

DOI10.1109/18.720534zbMath0933.94008OpenAlexW2294584261MaRDI QIDQ4701188

Neri Merhav, Meir Feder

Publication date: 21 November 1999

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL: https://semanticscholar.org/paper/50f8b27297425b6bab118dda625dd63809c7c3f8




Related Items (75)

Adaptive strategies in Kelly’s horse races modelON DETERMINISTIC FINITE STATE MACHINES IN RANDOM ENVIRONMENTSA universal online caching algorithm based on pattern matchingOn universal prediction and Bayesian confirmationAn Objective Bayesian Criterion to Determine Model Prior ProbabilitiesFast learning rates in statistical inference through aggregationReporting Bayes factors or probabilities to decision makers of unknown loss functionsUnnamed ItemA Bayesian approach to (online) transfer learning: theory and algorithmsA loss‐based prior for Gaussian graphical modelsOptimal, reliable estimation of quantum statesFractal dimension and logarithmic loss unpredictability.Objective prior for the number of degrees of freedom of a \(t\) distributionObjective Bayesian analysis of the Yule-Simon distribution with applicationsGeneralized self-concordant analysis of Frank-Wolfe algorithmsChasing Ghosts: Competing with Stateful PoliciesOn the mathematics of the Jeffreys–Lindley paradoxOptimal Sampling of Parametric Families: Implications for Machine LearningLoss-based approach to two-piece location-scale distributions with applications to dependent dataUniversal prediction of random binary sequences in a noisy environmentA loss-based prior for variable selection in linear regression methodsRandomized prediction of individual sequencesUnnamed ItemUnnamed ItemNonparametric sequential prediction for stationary processesOn the degree of univariate polynomials over the integersOnline portfolio selectionExplanatory and creative alternatives to the MDL principlePrediction and dimensionHigh-confidence predictions under adversarial uncertaintyQuantum rejection samplingCompressed matrix multiplicationOn a loss-based prior for the number of components in mixture modelsOn universal algorithms for classifying and predicting stationary processesSensor networks: from dependence analysis via matroid bases to online synthesisOn calibration error of randomized forecasting algorithmsMeasuring the efficiency of the intraday Forex market with a universal data compression algorithmLearning hurdles for sleeping expertsRestriction accessMechanism design with approximate valuationsQuantum strategic game theoryThe curse of simultaneityNo justified complaintsFrom randomizing polynomials to parallel algorithmsPractical verified computation with streaming interactive proofsPaging for multi-core shared cachesNoise vs computational intractability in dynamicsDistribution free evolvability of polynomial functions over all convex loss functionsAlgorithms on evolving graphsTowards deterministic tree code constructionsLinear time decoding of regular expander codesList decoding subspace codes from insertions and deletionsBounds on locally testable codes with unique testsApproximately optimal mechanism design via differential privacyFairness through awarenessDynamics of prisoner's dilemma and the evolution of cooperation on networksCrowdsourced Bayesian auctionsSuper-polynomial quantum speed-ups for boolean evaluation trees with hidden structureQuantum interactive proofs with weak error boundsQuantum money from knots(Leveled) fully homomorphic encryption without bootstrappingFrom extractable collision resistance to succinct non-interactive arguments of knowledge, and back againTargeted malleabilitySherali-Adams relaxations and indistinguishability in counting logicsGraph densificationSpectral sparsification via random spannersMulticommodity flows and cuts in polymatroidal networksOn persistent homotopy, knotted complexes and the Alexander moduleGadgets and anti-gadgets leading to a complexity dichotomyOn beating the hybrid argumentLinear programming, width-1 CSPs, and robust satisfactionMarginal hitting sets imply super-polynomial lower bounds for permanentOn prediction of individual sequencesUnnamed ItemOn asymptotically optimal methods of prediction and adaptive coding for Markov sources




This page was built for publication: Universal prediction