9 citations · 24 across the 8 of their papers we have counts for
8 papers
Training with Mixed-Precision Floating-Point Assignments
Wonyeol Lee, Rahul Sharma, Alex Aiken
When training deep neural networks, keeping all tensors in high precision (e.g., 32-bit or even 16-bit floats) is often wasteful. However, keeping all tensors in low precision (e.g…
On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters
Wonyeol Lee, Sejun Park, Alex Aiken
Recent work has shown that forward- and reverse- mode automatic differentiation (AD) over the reals is almost always correct in a mathematically precise sense. However, actual prog…
Smoothness Analysis for Probabilistic Programs with Application to Optimised Variational Inference
Wonyeol Lee, Xavier Rival, Hongseok Yang
We present a static analysis for discovering differentiable or more generally smooth parts of a given probabilistic program, and show how the analysis can be used to improve the pa…
On Correctness of Automatic Differentiation for Non-Differentiable Functions
Wonyeol Lee, Hangyeol Yu, Xavier Rival +1
Differentiation lies at the core of many machine-learning algorithms, and is well-supported by popular autodiff systems, such as TensorFlow and PyTorch. Originally, these systems h…
Differentiable Algorithm for Marginalising Changepoints
Hyoungjin Lim, Gwonsoo Che, Wonyeol Lee +1
We present an algorithm for marginalising changepoints in time-series models that assume a fixed number of unknown changepoints. Our algorithm is differentiable with respect to its…
Towards Verified Stochastic Variational Inference for Probabilistic Programs
Wonyeol Lee, Hangyeol Yu, Xavier Rival +1
Probabilistic programming is the idea of writing models from statistics and machine learning using program notations and reasoning about these models using generic inference engine…