Statistical Learning
GloballyConvergentNewtonMethodsfor Ill-conditionedGeneralizedSelf-concordantLosses
Second, in the non-parametric machine learning setting, we provide an explicit algorithm combining the previous scheme with Nyström projection techniques, andprovethatitachievesoptimal generalization bounds with atime complexity of orderO(ndfλ), a memory complexity of orderO(df2λ) and no dependence on the condition number, generalizing the results known for leastsquaresregression.Here nisthenumberofobservationsand dfλ istheassociated degrees of freedom.
HGDL: Heterogeneous Graph Label Distribution Learning
Each distribution quantifies the descriptive degrees of various classes given a specific instance.
Learning to Learn By Self-Critique
Antreas Antoniou, Amos J. Storkey
Neural Information Processing Systems http://nips.cc/
Statistical and Computational Trade-Offs in Kernel K-Means
Daniele Calandriello, Lorenzo Rosasco
More precisely, we study a Nyström approach to kernel k-means. Weanalyze thestatistical properties oftheproposed method andshow that it achieves the same accuracy of exact kernel k-means with only a fraction of computations.
Variational Gaussian Processes For Linear Inverse Problems
By now Bayesian methods are routinely used in practice for solving inverse problems.