Mike Wu
334 Jordan Hall
me@mikehwu.com

I'm a third year PhD student in Computer Science at Stanford University advised by Noah Goodman. I'm interested in more efficient learning algorithms using weak- and self- supervision.

I did my undergrad in CS at Yale ('16) where I worked on astrostatistics. Then, I took a year off before starting graduate school, where I worked at Facebook Research. I also helped found a startup building a probabilistic programming language in Excel called Invrea.

Some of the amazing researchers I like to work with: Chris Piech, Stefano Ermon, Dan Yamins, Michael C. Hughes, Finale Doshi-Velez, Frank Wood, Kristy Choi, Chengxu Zhuang, Ali Malik, Milan Mosse, Conner Vercellino


Recent News
  • Stanford Interdisciplinary Graduate Fellowship: I am excited to be supported by SIGF to continue work in AI+education.
  • Best paper awards: I am humbled to have received recent best paper awards from EDM'20 [paper] and AAAI'19 [paper].

Mike Wu
334 Jordan Hall
me@mikehwu.com

I'm a third year PhD student in Computer Science at Stanford University advised by Noah Goodman. I'm interested in more efficient learning algorithms using weak- and self- supervision.

I did my undergrad in CS at Yale ('16) where I worked on astrostatistics. Then, I took a year off before starting graduate school, where I worked at Facebook Research. I also helped found a startup building a probabilistic programming language in Excel called Invrea.

Some of the amazing researchers I like to work with: Chris Piech, Stefano Ermon, Dan Yamins, Chelsea Finn, Finale Doshi-Velez, Frank Wood, Michael C. Hughes, Kristy Choi, Chengxu Zhuang,Ali Malik, Milan Mosse, Conner Vercellino

Recent News
  • Stanford Interdisciplinary Graduate Fellowship: I am excited to be supported by SIGF to continue work in AI+education.
  • Best paper awards: I am humbled to have received recent best paper awards from EDM'20 [paper] and AAAI'19 [paper].

Preprints

ArXiv
On Mutual Information in Contrastive Learning for Visual Representations

Mike Wu, Chengxu Zhuang, Milan Mosse, Daniel Yamins, Noah Goodman

V1 PDF V0 PDF
Submitted to JMLR
Multimodal Generative Models for Compositional Representation Learning

Mike Wu, Noah Goodman

PDF
Submitted to JAIR
Optimizing for Interpretability in Deep Neural Networks with Simulable Decision Trees

Mike Wu, Sonali Parbhoo, Michael C. Hughes, Volker Roth, Finale Doshi-Velez

PDF

Publications

EDM 2020
Variational Item Response Theory: Fast, Accurate, and Expressive

Mike Wu, Richard L. Davis, Benjamin W. Domingue, Chris Piech, Noah Goodman

PDF Oral Best Paper
ArXiv
Generative Grading: Neural Approximate Parsing for Automated Student Feedback

Ali Malik (*), Mike Wu (*), Vrinda Vasavada, Jinpeng Song, John Mitchell, Noah Goodman, Chris Piech

PDF
AAAI 2020
Regional Tree Regularization for Interpretability in Black Box Models

Mike Wu, Sonali Parbhoo, Michael C. Hughes, Ryan Kindle, Leo Celi, Maurizio Zazzi, Volker Roth, Finale Doshi-Velez

PDF Oral
AAAI 2020, NeurIPS BDL 2019
Meta-Amortized Variational Inference and Learning

Mike Wu (*), Kristy Choi (*), Noah Goodman, Stefano Ermon

PDF BDL Oral
COBB 2019
Pragmatic inference and Visual Abstraction Enable Contextual Flexibility during Visual Communication

Judith Fan, Robert X.D. Hawkins, Mike Wu, Noah Goodman

PDF
AISTATS 2019
Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference

Mike Wu, Noah Goodman, Stefano Ermon

PDF
AAAI 2019
Zero Shot Learning for CodeEducation: Rubric Sampling with Deep Learning Inference

Mike Wu, Milan Mosse, Noah Goodman, Chris Piech

PDF Oral Best Student Paper
NeurIPS 2018
Multimodal Generative Models for Scalable Weakly Supervised Learning

Mike Wu, Noah Goodman

PDF
PROBPROG 2018
Spreadsheet Probabilistic Programming

Mike Wu, Yura Perov, Frank Wood, Hongseok Yang, William Smith

PDF
AAAI 2017, NeurIPS TiML 2017
Tree Regularization of Deep Models for Interpretability

Mike Wu, Michael C. Hughes, Sonali Parbhoo, Maurizio Zazzi, Volker Roth, Finale Doshi-Velez

PDF AAAI Oral TiML Oral
AMIA CRI 2017
Predicting Intervention Onset in the ICU with Switching Statespace Models

Marzyeh Ghassemi, Mike Wu, Michael C. Hughes, Finale Doshi-Velez

PDF Oral Best Paper Finalist
JAMIA 2016
Understanding Vassopressor Intervention and Weaning: Risk Prediction in a Public Heterogeneous Clinical Time Series Database

Mike Wu, Marzyeh Ghassemi, Mengling Feng, Leo Anthony Celi, Peter Szolovitz, Finale Doshi-Velez

PDF
IJCSI 2013
Edge-based Crowd Detection from Single Image Datasets

Mike Wu, Madhu Krishnan

PDF
ARPN 2012, ISEF Semifinalist 2012
Autonomous Mapping and Navigation through Utilization of Edge-based Optical Flow and Time-to-Collision

Madhu Krishnan, Mike Wu, Young Kang, Sarah H. Lee

PDF

Conference Abstracts

VSS 2018
Modeling Contextual Flexibility in Visual Communication

Judith Fan, Robert X.D. Hawkins, Mike Wu, Noah Goodman

AAS 2018, Undergrad Thesis
Investigating the Cosmic Web with Topological Data Analysis

Jessi Cisewski-Kehe, Mike Wu, Brittany Fasy, Wojciech Hellwing, Mark Lovell, Alessandro Rinaldo, Larry Wasserman

XSEDE 2011, Siemens Semifinalist 2012, ISEF Finalist 2011: 3rd place
Position and Vector Detection of Blind Spot motion with the Horn-Schunck Optical Flow

Stephen Yu, Mike Wu

XSEDE Best Student Poster