Wonyeol Lee

Registered user since Fri 3 Jul 2015

Name:Wonyeol Lee
Bio:

Wonyeol Lee is a final year PhD student in Computer Science at Stanford University advised by Alex Aiken. In 2017-2020, he was a researcher at KAIST to serve mandatory military service, working with Hongseok Yang. He received a BS degree in Computer Science & Mathematics from POSTECH. He is a recipient of the Samsung Scholarship.

He likes to raise and solve fundamental / theoretical questions in programming languages (PL) and machine learning (ML) that are connected to practice. In particular, he is interested in identifying and addressing various challenges in ML that arise from discrepancies between the theory and practice of ML, especially the following: in theory, mathematical functions of interest are assumed to be “well-behaved”, but in practice, they are represented by programs which can be easily “ill-behaved”.

Country:United States
Affiliation:Stanford University
Personal website:https://wonyeol.github.io
Research interests:Correctness (verification | program analysis), Numerical Programs (probabilistic | differentiable | floating-point), Differentiation (non-differentiability | automatic differentiation | gradient estimation), Probabilistic Inference (variational inference)

Contributions

POPL 2023 Author of Smoothness Analysis for Probabilistic Programs with Application to Optimised Variational Inference within the POPL-track
POPL 2020 Committee Member in Artifact Evaluation Committee within the Artifact Evaluation-track
Author of Towards Verified Stochastic Variational Inference for Probabilistic Programs within the Research Papers-track
POPL 2018 Author of On Automatically Proving the Correctness of math.h Implementations within the Research Papers-track
PLDI 2016 Author of Verifying Bit Manipulations of Floating-Point within the Research Papers-track