I am a PhD student at Stanford, where I am advised by Noah Goodman. My current research interests are in bayesian deep learning, sampling methods, and inference in generative models. I am supported by the NSF GRFP grant.
I completed my undergrad in computer science at Yale University ('16). I also briefly spent time abroad at University of Oxford with Frank Wood, and at Harvard with Finale Doshi-Velez.
Mike Wu, Noah Goodman, Stefano Ermon. Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference. ArXiv, 2019.
Mike Wu, Milan Mosse, Noah Goodman, Chris Piech. Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference. ArXiv, 2019.
Mike Wu, Noah Goodman. Multimodal Generative Models for Scalable Weakly-Supervised Learning. Neural Information Processing Systems (NIPS), 2018.
Mike Wu, Yura Perov, Frank Wood, Hongseok Yang, William Smith. Spreadsheet Probabilistic Programming. The International Conference on Probabilistic Programming (PROBPROG), 2018.
Mike Wu, Michael C. Hughes, Sonali Parbhoo, Maurizio Zazzi, Volker Roth, Finale Doshi-Velez. Beyond Sparsity: Tree Regularization of Deep Models for Interpretability. Association for the Advancement of Artificial Intelligence (AAAI), 2018. Spotlight presentation.
Marzyeh Ghassemi, Mike Wu, Michael C. Hughes, Finale Doshi-Velez. Predicting intervention onset in the ICU with switching statespace models. Joint Summits on Translational Science (AMIA), 2017. Nominated for Clinical Informatics Research Award.
Mike Wu, Marzyeh Ghassemi, Mengling Feng, Leo Anthony Celi, Peter Szolovitz, Finale Doshi-Velez. Understanding vasopressor intervention and weaning: Risk prediction in a public heterogeneous clinical time series database. Journal of the American Medical Informatics Association (JAMIA), 2016.
Mike Wu, Madhu Krishnan. Edge-based Crowd Detection from Single Image Datasets. International Journal of Computer Science Issues (IJCSI), 2013.
Madhu Krishnan, Mike Wu, Young Kang, Sarah Lee. Autonomous Mapping and Navigation through Utilization of Edge-based Optical Flow and Time-to-Collision. ARPN Journal of Engineering and Applied Sciences, 2012.
Mike Wu. Financial Market Prediction Using Self-Organizing Maps. arXiv, 2015. Oxford Deep Learning course project.
Stephen Yu, Mike Wu. Position and Vector Detection of Blind Spot motion with the Horn-Schunck Optical Flow. arXiv, 2011. Intel ISEF Finalist: Third place category award, 2011. Siemens Semifinalist, 2012. XSEDE Best student poster, 2011.
Co-founded YHack in 2013.
Augmented reality prize. Angelhack, 2018.
Telesign API 1st place prize. API World hackathon, 2017.
First place prize. Truface.ai hackathon, 2017.
Top 8 projects. Dropbox API prize. HackMIT, 2014.