scientific article; zbMATH DE number 5957285

MaRDI QIDQ3093288zbMATH OpenFDO

Authors Koji Tsuda, Gunnar Rätsch, Manfred K. Warmuth

Publication date 12 October 2011

Full work available at URL http://www.jmlr.org/papers/v6/tsuda05a.html

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Matrix-update for accelerated on-line learning in multilayer neural networks
• Bregman proximal gradient algorithms for deep matrix factorization
• Online Learning With Inexact Proximal Online Gradient Descent Algorithms
• Incrementally updated gradient methods for constrained and regularized optimization
• Online Covariance Matrix Estimation in Stochastic Gradient Descent
• Gradient-based sparse principal component analysis with extensions to online learning
• scientific article; zbMATH DE number 1263196
• scientific article; zbMATH DE number 1916734
• Online optimization for max-norm regularization

Cited in

(19)

• Low-rank decomposition meets kernel learning: a generalized Nyström method
• Bayesian generalized probability calculus for density matrices
• Convergence of the exponentiated gradient method with Armijo line search
• Kernelization of matrix updates, when and how?
• Skew Jensen-Bregman Voronoi diagrams
• Online variance minimization
• Kernelization of matrix updates, when and how?
• Affine invariant divergences associated with proper composite scoring rules and their applications
• Some universal insights on divergences for statistics, machine learning and artificial intelligence
• Scalable semidefinite programming
• Near-optimal algorithms for online matrix prediction
• On the convergence of mirror descent beyond stochastic convex programming
• Online learning of quantum states
• Negativizability: a useful property for distributed state estimation and control in cyber-physical systems
• The rate of convergence of Bregman proximal methods: local geometry versus regularity versus sharpness
• Eigenvalue problems via the multiplicative weights update method
• Exponentiated gradient meets gradient descent
• Generalize across tasks: efficient algorithms for linear representation learning
• Learning the kernel matrix by maximizing a KFD-based class separability criterion

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3093288)