7 papers
Universal Denoising without Channel Knowledge
Matthias Frey, Jonathan H. Manton, Jingge Zhu
Inspired by a classical algorithm for online prediction, we propose a novel denoising scheme which is universal for families of probability distributions both in terms of the sourc…
A PAC-Bayes Approach for Controlling Unknown Linear Discrete-time Systems
Yujia Luo, Ye Pu, Jonathan H. Manton +1
This paper presents a PAC-Bayes framework for learning controllers for unknown stochastic linear discrete-time systems, where the system parameters are drawn from a fixed but unkno…
FastICA with Learned Scores from the Empirical Characteristic Function
David Watts, Jonathan H. Manton
Independent component analysis (ICA) estimates a demixing matrix that can recover statistically independent sources from linear mixtures. FastICA is a popular ICA algorithm due to…
Online Prediction of Stochastic Sequences with High Probability Regret Bounds
Matthias Frey, Jonathan H. Manton, Jingge Zhu
We revisit the classical problem of universal prediction of stochastic sequences with a finite time horizon known to the learner. The question we investigate is whether it is p…
An Asynchronous Decentralised Optimisation Algorithm for Nonconvex Problems
Behnam Mafakheri, Jonathan H. Manton, Iman Shames
In this paper, we consider nonconvex decentralised optimisation and learning over a network of distributed agents. We develop an ADMM algorithm based on the Randomised Block Coordi…
Emergence of Computational Structure in a Neural Network Physics Simulator
Rohan Hitchcock, Gary W. Delaney, Jonathan H. Manton +2
Neural networks often have identifiable computational structures - components of the network which perform an interpretable algorithm or task - but the mechanisms by which these em…