Relative loss bounds for on-line density estimation with the exponential family of distributions
From MaRDI portal
Publication:5945695
DOI10.1023/A:1010896012157zbMath0988.68173arXiv1301.6677MaRDI QIDQ5945695
Katy S. Azoury, Manfred K. Warmuth
Publication date: 22 July 2002
Published in: Machine Learning (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1301.6677
68T05: Learning and adaptive systems in artificial intelligence
68T20: Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.)
Related Items
Unnamed Item, Unnamed Item, Unnamed Item, Monte Carlo Information-Geometric Structures, On the Bias, Risk, and Consistency of Sample Means in Multi-armed Bandits, Quasiconvex Jensen Divergences and Quasiconvex Bregman Divergences, Online Learning Based on Online DCA and Application to Online Classification, Adaptive and optimal online linear regression on \(\ell^1\)-balls, Learning noisy linear classifiers via adaptive and selective sampling, Weighted last-step min-max algorithm with improved sub-logarithmic regret, Kernelization of matrix updates, when and how?, A generalized online mirror descent with applications to classification and regression, Classification into Kullback-Leibler balls in exponential families, Leading strategies in competitive on-line prediction, A primal-dual perspective of online learning algorithms, Adaptive and self-confident on-line learning algorithms, Relative expected instantaneous loss bounds, Smooth calibration, leaky forecasts, finite recall, and Nash dynamics, A quasi-Bayesian perspective to online clustering, Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory, Deformed statistics Kullback-Leibler divergence minimization within a scaled Bregman framework, Multiclass classification with bandit feedback using adaptive regularization, Sequential model aggregation for production forecasting, Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices, Suboptimality of constrained least squares and improvements via non-linear predictors, Distribution-free robust linear regression, Computing statistical divergences with sigma points, Learning rates of gradient descent algorithm for classification, An Upper Bound for Aggregating Algorithm for Regression with Changing Dependencies, Online regularized generalized gradient classification algorithms, Aggregating Algorithm for a Space of Analytic Functions, New aspects of Bregman divergence in regression and classification with parametric and nonparametric estimation
