Timezone: »

 
Poster
Nonparametric Score Estimators
Yuhao Zhou · Jiaxin Shi · Jun Zhu

Tue Jul 14 08:00 AM -- 08:45 AM & Tue Jul 14 09:00 PM -- 09:45 PM (PDT) @
in Poster Session 2 »

Estimating the score, i.e., the gradient of log density function, from a set of samples generated by an unknown distribution is a fundamental task in inference and learning of probabilistic models that involve flexible yet intractable densities. Kernel estimators based on Stein's methods or score matching have shown promise, however their theoretical properties and relationships have not been fully-understood. We provide a unifying view of these estimators under the framework of regularized nonparametric regression. It allows us to analyse existing estimators and construct new ones with desirable properties by choosing different hypothesis spaces and regularizers. A unified convergence analysis is provided for such estimators. Finally, we propose score estimators based on iterative regularization that enjoy computational benefits from curl-free kernels and fast convergence.

Keywords: Approximate Inference · Kernel Methods · Spectral Methods · General Machine Learning Techniques

Author Information

Yuhao Zhou (Tsinghua University)
Jiaxin Shi (Tsinghua University)
Jun Zhu (Tsinghua University)

More from the Same Authors