Exponentiated gradient versus gradient descent for linear predictors
From MaRDI portal
Publication:675044
DOI10.1006/inco.1996.2612zbMath0872.68158OpenAlexW2069317438WikidataQ100380108 ScholiaQ100380108MaRDI QIDQ675044
Manfred K. Warmuth, Jyrki Kivinen
Publication date: 19 October 1997
Published in: Information and Computation (Search for Journal in Brave)
Full work available at URL: https://semanticscholar.org/paper/4e77fb934237e164ec090617a66de381ef0661a0
Related Items
Improved algorithms for online load balancing, Limited Stochastic Meta-Descent for Kernel-Based Online Learning, Adaptive stepsizes for recursive estimation with applications in approximate dynamic programming, Unnamed Item, Competitive On-line Statistics, Adaptive regularization of weight vectors, The Perceptron algorithm versus Winnow: linear versus logarithmic mistake bounds when few input variables are relevant, Efficient learning with virtual threshold gates, Adaptive and optimal online linear regression on \(\ell^1\)-balls, PAC-Bayesian risk bounds for group-analysis sparse regression by exponential weighting, Convergence of the exponentiated gradient method with Armijo line search, Regrets of proximal method of multipliers for online non-convex optimization with long term constraints, Testing for association in multiview network data, Learning rotations with little regret, Distributed online bandit linear regressions with differential privacy, Optimistic optimisation of composite objective with exponentiated update, Convergence rates of gradient methods for convex optimization in the space of measures, Foraging theory for dimensionality reduction of clustered data, Nonstationary online convex optimization with multiple predictions, Online variance minimization, A kernel-based perceptron with dynamic memory, Recursive aggregation of estimators by the mirror descent algorithm with averaging, Scale-free online learning, Randomized Linear Programming Solves the Markov Decision Problem in Nearly Linear (Sometimes Sublinear) Time, An efficient approach to solve the large-scale semidefinite programming problems, Dynamical memory control based on projection technique for online regression, Cutting-plane training of structural SVMs, Bayesian generalized probability calculus for density matrices, Extracting certainty from uncertainty: regret bounded by variation in costs, Online Decision Making with High-Dimensional Covariates, Online Learning Based on Online DCA and Application to Online Classification, Weighted last-step min-max algorithm with improved sub-logarithmic regret, PORTFOLIO SELECTION AND ONLINE LEARNING, Analysis of two gradient-based algorithms for on-line regression, Online Ranking by Projecting, A generalized online mirror descent with applications to classification and regression, RECURSIVE FORECAST COMBINATION FOR DEPENDENT HETEROGENEOUS DATA, A continuous-time approach to online optimization, Neural learning by geometric integration of reduced `rigid-body' equations, The Concave-Convex Procedure, Multiplicative Updates for Nonnegative Quadratic Programming, A quasi-Bayesian perspective to online clustering, Learning to Assign Degrees of Belief in Relational Domains, A modular analysis of adaptive (non-)convex optimization: optimism, composite objectives, variance reduction, and variational bounds, Relative utility bounds for empirically optimal portfolios, An entropic Landweber method for linear ill-posed problems, A primal-dual perspective of online learning algorithms, Competing with wild prediction rules, Learning to assign degrees of belief in relational domains, Constrained dual graph regularized orthogonal nonnegative matrix tri-factorization for co-clustering, Robust and sparse regression in generalized linear model by stochastic optimization, A game of prediction with expert advice, Worst-case analysis of the Perceptron and Exponentiated Update algorithms, Achieving fairness with a simple ridge penalty, On the Convergence of Mirror Descent beyond Stochastic Convex Programming, Online Learning of Nash Equilibria in Congestion Games, Out-of-Sample Utility Bounds for Empirically Optimal Portfolios in a Single-Period Investment Problem
