When Gaussian process meets big data: A review of scalable GPs

H Liu, YS Ong, X Shen, J Cai - IEEE transactions on neural …, 2020 - ieeexplore.ieee.org
The vast quantity of information brought by big data as well as the evolving computer
hardware encourages success stories in the machine learning community. In the …

Variational continual learning

CV Nguyen, Y Li, TD Bui, RE Turner - arXiv preprint arXiv:1710.10628, 2017 - arxiv.org
This paper develops variational continual learning (VCL), a simple but general framework
for continual learning that fuses online variational inference (VI) and recent advances in …

Functional regularisation for continual learning with gaussian processes

MK Titsias, J Schwarz, AGG Matthews… - arXiv preprint arXiv …, 2019 - arxiv.org
We introduce a framework for Continual Learning (CL) based on Bayesian inference over
the function space rather than the parameters of a deep neural network. This method …

Bayesian optimization of nanoporous materials

A Deshwal, CM Simon, JR Doppa - Molecular Systems Design & …, 2021 - pubs.rsc.org
Nanoporous materials (NPMs) could be used to store, capture, and sense many different
gases. Given an adsorption task, we often wish to search a library of NPMs for the one with …

A unifying framework for Gaussian process pseudo-point approximations using power expectation propagation

TD Bui, J Yan, RE Turner - Journal of Machine Learning Research, 2017 - jmlr.org
Gaussian processes (GPs) are flexible distributions over functions that enable highlevel
assumptions about unknown functions to be encoded in a parsimonious, flexible and …

Data-driven science and machine learning methods in laser–plasma physics

A Döpp, C Eberle, S Howard, F Irshad, J Lin… - High Power Laser …, 2023 - cambridge.org
Laser-plasma physics has developed rapidly over the past few decades as lasers have
become both more powerful and more widely available. Early experimental and numerical …

Non-parametric calibration for classification

J Wenger, H Kjellström… - … Conference on Artificial …, 2020 - proceedings.mlr.press
Many applications of classification methods not only require high accuracy but also reliable
estimation of predictive uncertainty. However, while many current classification frameworks …

Information-theoretic online memory selection for continual learning

S Sun, D Calandriello, H Hu, A Li, M Titsias - arXiv preprint arXiv …, 2022 - arxiv.org
A challenging problem in task-free continual learning is the online selection of a
representative replay memory from data streams. In this work, we investigate the online …

Continual learning via sequential function-space variational inference

TGJ Rudner, FB Smith, Q Feng… - … on Machine Learning, 2022 - proceedings.mlr.press
Sequential Bayesian inference over predictive functions is a natural framework for continual
learning from streams of data. However, applying it to neural networks has proved …

Gaussian process-based real-time learning for safety critical applications

A Lederer, AJO Conejo, KA Maier… - International …, 2021 - proceedings.mlr.press
The safe operation of physical systems typically relies on high-quality models. Since a
continuous stream of data is generated during run-time, such models are often obtained …