Learning rotations with little regret

DOI10.1007/S10994-016-5548-XMaRDI QIDQ1689555zbMATH OpenOpenAlexFDO

Authors Elad Hazan, Satyen Kale, Manfred K. Warmuth

Publication date 12 January 2018

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-016-5548-x

zbMATH Keywords

Bregman projectionminimaxonline learningregret boundsrotations

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12) Learning and adaptive systems in artificial intelligence (68T05) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05) Online algorithms; streaming algorithms (68W27)

Recommendations

• Randomized online PCA algorithms with regret bounds that are logarithmic in the dimension
• Logarithmic Regret Algorithms for Online Convex Optimization
• Logarithmic regret algorithms for online convex optimization
• Online PCA with optimal regret
• On-line learning of linear functions

Cites work

• A decision-theoretic generalization of on-line learning and an application to boosting
• A generalized solution of the orthogonal Procrustes problem
• Combining initial segments of lists
• Computer Algebra and Geometric Algebra with Applications
• Exponentiated gradient versus gradient descent for linear predictors
• Learning permutations with exponential weights
• Learning rotations with little regret
• Lie groups as spin groups
• Matrix mathematics. Theory, facts, and formulas
• Online variance minimization
• Steepest Descent Algorithms for Optimization Under Unitary Matrix Constraint
• The best constants in the Khintchine inequality
• Tracking the best linear predictor

Cited in

(2)

• Learning rotations with little regret
• Online PCA with optimal regret

Describes a project that uses

Uses Software

• AdaBoost.MH

This page was built for publication: Learning rotations with little regret

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1689555)