Contact

  • Academic
    mli1998@stanford.edu
    University - Student Department: Computer Science Position: Graduate

All Publications

  • Learning to Learn Functions. Cognitive science Li, M. Y., Callaway, F., Thompson, W. D., Adams, R. P., Griffiths, T. L. 2023; 47 (4): e13262

    Abstract

    Humans can learn complex functional relationships between variables from small amounts of data. In doing so, they draw on prior expectations about the form of these relationships. In three experiments, we show that people learn to adjust these expectations through experience, learning about the likely forms of the functions they will encounter. Previous work has used Gaussian processes-a statistical framework that extends Bayesian nonparametric approaches to regression-to model human function learning. We build on this work, modeling the process of learning to learn functions as a form of hierarchical Bayesian inference about the Gaussian process hyperparameters.

    View details for DOI 10.1111/cogs.13262

    View details for PubMedID 37051879

  • Why think step by step? Reasoning emerges from the locality of experience Prystawski, B., Li, M. Y., Goodman, N. D. edited by Oh, A., Neumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2023

    View details for Web of Science ID 001230083405036

  • NAS-<i>X</i>: Neural Adaptive Smoothing via Twisting Lawson, D., Li, M. Y., Linderman, S. W. edited by Oh, A., Neumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2023

    View details for Web of Science ID 001229751902029

  • Gaussian Process Surrogate Models for Neural Networks Li, M. Y., Grant, E., Griffiths, T. L. edited by Evans, R. J., Shpitser JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2023: 1241-1252

    View details for Web of Science ID 001222701100117