Publications

An up-to-date list may be found at Google Scholar

  • Kevin Ellis, Catherine Wong, Maxwell Nye, Mathias Sablé-Meyer, Luc Cary, Lucas Morales, Luke Hewitt, Armando Solar-Lezama, Josh Tenenbaum. DreamCoder: A wake-sleep algorithm for deep Bayesian program learning. In prep.

  • Maxwell Nye, Armando Solar-Lezama, Josh Tenenbaum, Brenden Lake. Learning Compositional Rules via Neural Program Synthesis. NeurIPS 2019, Workshop on Context and Compositionality in Biological and Artificial Neural Systems, in press.

  • Kevin Ellis*, Maxwell Nye*, Yewen Pu*, Felix Sosa*, Josh Tenenbaum, Armando Solar-Lezama. Write, Execute, Assess: Program Synthesis with a REPL. NeurIPS 2019, in press. paper

  • Maxwell Nye, Luke Hewitt, Josh Tenenbaum, Armando Solar-Lezama. Learning to Infer Program Sketches. ICML 2019. paper

  • Luke Hewitt, Maxwell Nye, Andreea Gane, Tommi Jaakkola, Josh Tenenbaum. The Variational Homoencoder: Learning to Infer High-Capacity Generative Models from Few Examples. UAI 2018, oral presentation. paper code

  • Maxwell Nye, Andrew Saxe. Are Efficient Deep Representations Learnable? ICLR 2018, workshop. paper