← Search

Erik Meijer

2 accepted papers

2022

Gradient Descent: The Ultimate Optimizer

NeurIPS 2022accept

Working with any gradient-based machine learning algorithm involves the tedious task of tuning the optimizer's hyperparameters, such as its step size. Recent work has shown how the step size can itself be optimized alongside the model parameters by manually deriving expressions for "hypergradients"…

2021

Accelerating Metropolis-Hastings with Lightweight Inference Compilation

AISTATS 2021poster

In order to construct accurate proposers for Metropolis-Hastings Markov Chain Monte Carlo, we integrate ideas from probabilistic graphical models and neural networks in an open-source framework we call Lightweight Inference Compilation (LIC). LIC implements amortized inference within an open-univers…