[social4i size="small" align="align-left"][This article was first published onR – Xi'an's Og, and kindly contributed toR-bloggers]. (You can report issue about the content on this pagehere)Want to share your content on R-bloggers?click hereif you have a blog, orhereif you don't.At theColumbia workshoplast week, Andre Wibisono presented work related with arecent arXivalon the exponentially fast convergence of both unadjusted Langevin and proximal sampler algorithms under strong [definitely strong] log-concavity assumptions. The idea behind the proximal sampler is to target the demar
...
继续阅读