179 citations · 221 across the 7 of their papers we have counts for
7 papers
Black-box Coreset Variational Inference
Dionysis Manousakas, Hippolyt Ritter, Theofanis Karaletsos
Recent advances in coreset methods have shown that a selection of representative datapoints can replace massive volumes of data for Bayesian inference, preserving the relevant stat…
TyXe: Pyro-based Bayesian neural nets for Pytorch
Hippolyt Ritter, Theofanis Karaletsos
We introduce TyXe, a Bayesian neural network library built on top of Pytorch and Pyro. Our leading design principle is to cleanly separate architecture, prior, inference and likeli…
Sparse Uncertainty Representation in Deep Learning with Inducing Weights
Hippolyt Ritter, Martin Kukla, Cheng Zhang +1
Bayesian neural networks and deep ensembles represent two modern paradigms of uncertainty quantification in deep learning. Yet these approaches struggle to scale mainly due to memo…
Addressing Catastrophic Forgetting in Few-Shot Problems
Pauching Yap, Hippolyt Ritter, David Barber
Neural networks are known to suffer from catastrophic forgetting when trained on sequential datasets. While there have been numerous attempts to solve this problem in large-scale s…
Gaussian Mean Field Regularizes by Limiting Learned Information
Julius Kunze, Louis Kirsch, Hippolyt Ritter +1
Variational inference with a factorized Gaussian posterior estimate is a widely used approach for learning parameters and hidden variables. Empirically, a regularizing effect can b…
Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting
Hippolyt Ritter, Aleksandar Botev, David Barber
We introduce the Kronecker factored online Laplace approximation for overcoming catastrophic forgetting in neural networks. The method is grounded in a Bayesian online learning fra…
Practical Gauss-Newton Optimisation for Deep Learning
Aleksandar Botev, Hippolyt Ritter, David Barber
We present an efficient block-diagonal ap- proximation to the Gauss-Newton matrix for feedforward neural networks. Our result- ing algorithm is competitive against state- of-the-ar…