Abstract | ||
---|---|---|
We study the Gibbs sampling algorithm for continuous determinantal point processes. We show that, given a warm start, the Gibbs sampler generates a random sample from a continuous $k$-DPP defined on a $d$-dimensional domain by only taking $text{poly}(k)$ number of steps. As an application, we design an algorithm to generate random samples from $k$-DPPs defined by a spherical Gaussian kernel on a unit sphere in $d$-dimensions, $mathbb{S}^{d-1}$ in time polynomial in $k,d$. |
Year | Venue | Field |
---|---|---|
2018 | arXiv: Learning | Applied mathematics,Mathematical optimization,Polynomial,Markov chain Monte Carlo,Point process,Sampling (statistics),Time complexity,Gaussian function,Gibbs sampling,Mathematics,Unit sphere |
DocType | Volume | Citations |
Journal | abs/1810.08867 | 0 |
PageRank | References | Authors |
0.34 | 0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shayan Oveis Gharan | 1 | 323 | 26.63 |
A. Rezaei | 2 | 0 | 2.03 |