2 search results - page 1 / 1 » Fast Algorithms for Logconcave Functions: Sampling, Rounding... |
FOCS
2006
IEEE
13 years 11 months ago
2006
IEEE
We prove that the hit-and-run random walk is rapidly mixing for an arbitrary logconcave distribution starting from any point in the support. This extends the work of [26], where t...
ESANN
2006
13 years 6 months ago
2006
Neural gas (NG) constitutes a very robust clustering algorithm which can be derived as stochastic gradient descent from a cost function closely connected to the quantization error...