2 papers
cs.LG2024
Diagonalisation SGD: Fast & Convergent SGD for Non-Differentiable Models via Reparameterisation and Smoothing
Dominik Wagner, Basim Khajwal, C. -H. Luke Ong
It is well-known that the reparameterisation gradient estimator, which exhibits low variance in practice, is biased for non-differentiable models. This may compromise correctness o…
cs.PL2023
Fast and Correct Gradient-Based Optimisation for Probabilistic Programming via Smoothing
Basim Khajwal, C. -H. Luke Ong, Dominik Wagner
We study the foundations of variational inference, which frames posterior inference as an optimisation problem, for probabilistic programming. The dominant approach for optimisatio…