Skip to yearly menu bar Skip to main content


Neurally-Guided Structure Inference

Sidi Lu · Jiayuan Mao · Josh Tenenbaum · Jiajun Wu

Pacific Ballroom #233

Keywords: [ Others ] [ Bayesian Methods ]


Most structure inference methods either rely on exhaustive search or are purely data-driven. Exhaustive search robustly infers the structure of arbitrarily complex data, but it is slow. Data-driven methods allow efficient inference, but do not generalize when test data have more complex structures than training data. In this paper, we propose a hybrid inference algorithm, the Neurally-Guided Structure Inference (NG-SI), keeping the advantages of both search-based and data-driven methods. The key idea of NG-SI is to use a neural network to guide the hierarchical, layer-wise search over the compositional space of structures. We evaluate our algorithm on two representative structure inference tasks: probabilistic matrix decomposition and symbolic program parsing. It outperforms data-driven and search-based alternatives on both tasks.

Live content is unavailable. Log in and register to view live content