Large-scale kernel machines

322 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Quasi-Monte Carlo Feature Maps for Shift-Invariant Kernels (2014, methodology): “For a broader discussion of these methods, and others, see Bottou et al. (2007). 2.”
Min-Max Kernels (2015, background): “It is well understood [3] that computing kernels are expensive and the kernel matrix, if fully materialized, does not ﬁt in memory even for relatively small applications.”
Taxonomic Prediction with Tree-Structured Covariances (2013, unknown): “2 This indicates that the resulting memory requirements for such a scheme are O(n2k2), while making use of optimization with Equation (14) requires only O(n2 + k(2) + nk) memory, and standard large scale kernel learning methods may be applied off-the-shelf to reduce the dominating O(n2) component [2”
High-Performance Kernel Machines With Implicit Distributed Optimization and Randomization (2014, background): “As such, with the growth in data across a multitude of applications, scaling up kernel methods [11] has acquired renewed and somewhat urgent significance.”