18 citations · 65 across the 9 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
stat.ML2023
Warped geometric information on the optimisation of Euclidean functions
Marcelo Hartmann, Bernardo Williams, Hanlin Yu +3
We consider the fundamental task of optimising a real-valued function defined in a potentially high-dimensional Euclidean space, such as the loss function in many machine-learning…
cs.LG2023
Scalable Stochastic Gradient Riemannian Langevin Dynamics in Non-Diagonal Metrics
Hanlin Yu, Marcelo Hartmann, Bernardo Williams +1
Stochastic-gradient sampling methods are often used to perform Bayesian inference on neural networks. It has been observed that the methods in which notions of differential geometr…