Skip to content
Sagan

Paper

State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives

Unreadunread

AI summary

arXiv:2605. 13127v1 Announce Type: new Abstract: Determinantal point processes (DPPs) have emerged as a kernelized alternative to vanilla independent sampling for generating efficient minibatches, coresets and other parsimonious representations of large-scale datasets.