Sciweavers

ICML
2009
IEEE

Herding dynamical weights to learn

14 years 11 months ago
Herding dynamical weights to learn
A new "herding" algorithm is proposed which directly converts observed moments into a sequence of pseudo-samples. The pseudosamples respect the moment constraints and may be used to estimate (unobserved) quantities of interest. The procedure allows us to sidestep the usual approach of first learning a joint model (which is intractable) and then sampling from that model (which can easily get stuck in a local mode). Moreover, the algorithm is fully deterministic, avoiding random number generation) and does not need expensive operations such as exponentiation.
Max Welling
Added 17 Nov 2009
Updated 17 Nov 2009
Type Conference
Year 2009
Where ICML
Authors Max Welling
Comments (0)