Barp, A; Briol, F-X; Duncan, AB; Girolami, MA; Mackey, LW; (2019) Minimum Stein Discrepancy Estimators. In: Wallach, H and Larochelle, H and Beygelzimer, A and d'Alché-Buc, F and Fox, E and Garnett., R, (eds.) Proceedings of Advances in Neural Information Processing Systems 32 (NIPS 2019). NIPS: Massachusetts, USA.

Preview

Text KSD-Arxiv.pdf - Accepted Version Available under License : See the attached licence file. Download (823kB) | Preview

Abstract

When maximum likelihood estimation is infeasible, one often turns to score matching, contrastive divergence, or minimum probability flow to obtain tractable parameter estimates. We provide a unifying perspective of these techniques as minimum Stein discrepancy estimators, and use this lens to design new diffusion kernel Stein discrepancy (DKSD) and diffusion score matching (DSM) estimators with complementary strengths. We establish the consistency, asymptotic normality, and robustness of DKSD and DSM estimators, then derive stochastic Riemannian gradient descent algorithms for their efficient optimisation. The main strength of our methodology is its flexibility, which allows us to design estimators with desirable properties for specific models at hand by carefully selecting a Stein discrepancy. We illustrate this advantage for several challenging problems for score matching, such as non-smooth, heavy-tailed or light-tailed densities.

Download activity - last month

Export as JSONCSVXML

Download activity - last 12 months

Export as JSONXMLCSV

Downloads by country - last 12 months

Export as JSONXMLCSV

Archive Staff Only

View Item