Wonyeol Lee

Postdoctoral Associate at CMU  |  wonyeol.lee.cs@gmail.com  |  CV

About Me

I am a Postdoctoral Associate at CMU CSD working with Feras Saad. I received a Ph.D. degree in Computer Science from Stanford University, where I was advised by Alex Aiken and supported by Samsung Scholarship. In 2017-2020, I was a researcher at KAIST to serve military service. I received a B.S. degree in Computer Science & Mathematics from POSTECH.

My research aims to broaden our theoretical understanding of continuous computations performed in practice and provide practical implications based on it. I am particularly interested in studying various gaps between the theory and practice of continuous computations and analyzing the correctness of these computations under these gaps.

Research Interests

• Correctness (provable guarantee | verification | program analysis)

• Continuous Computation (finite-precision | differentiable | probabilistic)

  • Finite Precision (floating point | elementary function | low precision)

  • Differentiation (non-differentiability | automatic differentiation | gradient estimation)

  • Probabilistic Inference (variational inference)

Publications

1. What Does Automatic Differentiation Compute for Neural Networks?
   Sejun Park, Sanghyuk Chun, Wonyeol Lee
   Submitted, 2023

2. Reasoning About Floating Point in Real-World Systems
   Wonyeol Lee
   Ph.D. Dissertation, 2023
   slides

3. On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters
   Wonyeol Lee, Sejun Park, Alex Aiken
   ICML 2023
   slides

4. Training with Mixed-Precision Floating-Point Assignments
   Wonyeol Lee, Rahul Sharma, Alex Aiken
   TMLR 2023
   code

5. Smoothness Analysis for Probabilistic Programs with Application to Optimised Variational Inference
   Wonyeol Lee, Xavier Rival, Hongseok Yang
   POPL 2023
   slides | video | code

6. On Correctness of Automatic Differentiation for Non-Differentiable Functions
   Wonyeol Lee, Hangyeol Yu, Xavier Rival, Hongseok Yang
   NeurIPS 2020 (Spotlight)
   slides (long) | video

7. Differentiable Algorithm for Marginalising Changepoints
   Hyoungjin Lim, Gwonsoo Che, Wonyeol Lee, Hongseok Yang
   AAAI 2020

8. Towards Verified Stochastic Variational Inference for Probabilistic Programs
   Wonyeol Lee, Hangyeol Yu, Xavier Rival, Hongseok Yang
   POPL 2020
   slides | video | code

9. Reparameterization Gradient for Non-Differentiable Models
   Wonyeol Lee, Hangyeol Yu, Hongseok Yang
   NeurIPS 2018
   slides | code

10. On Automatically Proving the Correctness of math.h Implementations
    Wonyeol Lee, Rahul Sharma, Alex Aiken
    POPL 2018
    slides (short) | video

11. Verifying Bit-Manipulations of Floating-Point
    Wonyeol Lee, Rahul Sharma, Alex Aiken
    PLDI 2016
    slides | video

12. A Proof System for Separation Logic with Magic Wand
    Wonyeol Lee, Sungwoo Park
    POPL 2014

13. CT-IC: Continuously Activated and Time-Restricted Independent Cascade Model for Viral Marketing
    Wonyeol Lee, Jinha Kim, Hwanjo Yu
    ICDM 2012
    journal | slides

14. Edge Detection Using Morphological Amoebas in Noisy Images
    Wonyeol Lee, Seyun Kim, Youngwoo Kim, Jaeyoung Lim, Dong Hoon Lim
    ICIP 2009
    journal

trips | last updated: 10/2023