Daniel D. Johnson

Education

University of Toronto  |  Toronto, ON, Canada
PhD, Computer Science
Sept 2021 - present
Harvey Mudd College  |  Claremont, CA  |  GPA: 3.98
Bachelor of Science, Joint Program in Computer Science and Mathematics
Aug 2014 - May 2018
Graduated with High Distinction and Honors in Computer Science, Mathematics, and Humanities

Work Experience

Research Scientist
Google Research, Brain team  |  Toronto, ON, Canada
Apr 2022 - present
previously, Research Software Engineer: June 2021 - Apr 2022
Continuing research on machine learning for software development, programming languages for machine learning, and reasoning under uncertainty about structured objects.
AI Resident
Google Research, Brain team  |  Montréal, QC, Canada
Oct 2019 - June 2021
Conducted research at the intersection of programming languages and machine learning.
Software Engineer  |  Perception
Cruise Automation  |  San Francisco, CA, USA
Full time: July 2018 - Sept 2019
Intern: May 2017 - Aug 2017
Developed machine learning models for self-driving cars.
Math and CS Grader and Tutor
Harvey Mudd College  |  Claremont, CA, USA
Aug 2015 - May 2018
Grader and tutor for Data Structures, Computability and Logic, Neural Networks, Discrete Mathematics, and HMC core math classes.
Software Engineering Intern
Pure Storage  |  Mountain View, CA, USA
May 2015 - Aug 2015
Wrote wrappers to manipulate C++ objects in existing codebase from Python. Extended internal Linux kernel testing framework using these wrappers to enable more direct tests and allow tests to run in multiple configurations.
Research Intern
Prof. Ron Frostig, Ph.D.  |  University of California, Irvine, CA, USA
Summer 2012, 2013
Developed tools in MATLAB to quantify neuronal density and automatically align overlapping microscope sections, which saving approximately 2000 hours of manual labor.

Publications

Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs
Daniel D. Johnson, Daniel Tarlow, David Duvenaud, Chris J. Maddison
[arXiv]
R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents
Daniel D. Johnson, Daniel Tarlow, Christian Walder
ICML 2023 [arXiv, code]
Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions
Daniel D. Johnson, Ayoub El Hanchi, Chris J. Maddison
ICLR 2023 [arXiv]
Parallel Algebraic Effect Handlers
Ningning Xie*, Daniel D. Johnson*, Dougal Maclaurin, Adam Paszke
ACM SIGPLAN Workshop on Partial Evaluation and Program Manipulation (PEPM) 2022 [arXiv, code]
Learning Generalized Gumbel-max Causal Mechanisms
Guy Lorberbom*, Daniel D. Johnson*, Chris J. Maddison, Daniel Tarlow, Tamir Hazan
NeurIPS 2021 (spotlight) [arXiv, code]
Structured denoising diffusion models in discrete state-spaces
Jacob Austin*, Daniel D. Johnson*, Jonathan Ho, Daniel Tarlow, Rianne van den Berg
NeurIPS 2021 [arXiv, code]
Beyond in-place corruption: Insertion and deletion in denoising probabilistic models
Daniel D. Johnson, Jacob Austin, Rianne van den Berg, Daniel Tarlow
2021 ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models [arXiv, code]
Getting to the point. Index sets and parallelism-preserving autodiff for pointful array programming
Adam Paszke, Daniel D. Johnson, David Duvenaud, Dimitrios Vytiniotis, Alexey Radul, Matthew Johnson, Jonathan Ragan-Kelley, Dougal Maclaurin
ICFP 2021 [arXiv, code]
Learning graph structure with a finite-state automaton layer
Daniel D. Johnson, Hugo Larochelle, Daniel Tarlow
NeurIPS 2020 (spotlight presentation); also presented at GRL+ 2020 [arXiv, talk, code]
Latent Gaussian Activity Propagation: Using smoothness and structure to separate and localize sounds in large noisy environments
Daniel D. Johnson, Daniel Gorelik, Ross E. Mawhorter, Kyle Suver, Weiqing Gu, Steven Xing, Cody Gabriel, Peter Sankhagowit
NeurIPS 2018 [pdf, poster]
Learning graphical state transitions
Daniel D. Johnson
ICLR 2017 (oral presentation) [pdf, talk, code, blogpost]
Learning to create jazz melodies using a product of experts
Daniel D. Johnson, Robert M. Keller, Nicholas Weintraut
International Conference on Computational Creativity 2017 [pdf, blogpost]
Generating polyphonic music with tied-parallel networks
Daniel D. Johnson
EvoMusArt 2017 [pdf, code, blogpost]
Geometric realizations of the 3D associahedron (multimedia exposition)
Satyan L. Devadoss, Daniel D. Johnson, Justin Lee, Jackson Warley
International Symposium on Computational Geometry 2017 [pdf, demo]
LEG processor for education
Maxwell Waugaman, Zakkai Davidson, Samuel Dietrich, Daniel Johnson, Cassandra Meyer, Eric Storm, Avi Thaker, Ivan Wong
European Workshop on Microelectronics Education 2016 [paper, blogpost]

Honors and Awards

  • NeurIPS Top 10% Reviewer (2020)
  • Computing Research Association Outstanding Undergraduate Researcher - Runner-up (2018)
  • Greever Clinic Award (Senior Capstone Project) (2018)
  • Barry Goldwater Scholar (2017)
  • Stavros Busenberg Prize for Outstanding Promise in Applied Mathematics (2017)
  • Robert James Prize for Outstanding Performance in Mathematics (2015)
  • Harvey S. Mudd Merit Award (2014-2018)
  • National Merit Scholar (2014)