Lee, Wonyeol

7 publications

ICML 2025 Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions Geonho Hwang, Yeachan Park, Wonyeol Lee, Sejun Park

ICLR 2024 What Does Automatic Differentiation Compute for Neural Networks? Sejun Park, Sanghyuk Chun, Wonyeol Lee

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

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

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

NeurIPS 2020 On Correctness of Automatic Differentiation for Non-Differentiable Functions Wonyeol Lee, Hangyeol Yu, Xavier Rival, Hongseok Yang

NeurIPS 2018 Reparameterization Gradient for Non-Differentiable Models Wonyeol Lee, Hangyeol Yu, Hongseok Yang