Jonathan Manton

Fast Rate Generalization Error Bounds: Variations on a Theme

X Wu, JH Manton, U Aickelin, J Zhu

Conference Proceedings  |  2022  |  Proceedings of the 2022 IEEE Information Theory Workshop, ITW 2022

A recent line of works, initiated by [1] and [2], has shown that the generalization error of a learning algorithm can be upper bou..

TRACKING AND REGRET BOUNDS FOR ONLINE ZEROTH-ORDER EUCLIDEAN AND RIEMANNIAN OPTIMIZATION

Alejandro Maass, Chris Manzie, Dragan Nesic, Jonathan H Manton, Iman Shames

Journal article  |  2022  |  SIAM JOURNAL ON OPTIMIZATION

We study numerical optimization algorithms that use zeroth-order information to minimize time-varying geodesically convex cost fun..

Computationally-Efficient Sparsely-Connected Multi-Output Neural Networks for IM/DD System Equalization

Z Xu, S Dong, H Ji, JH Manton, W Shieh

Conference Proceedings  |  2022  |  2022 Optical Fiber Communications Conference and Exhibition, OFC 2022 - Proceedings

Low-complexity sparsely-connected multi-output neural networks are proposed for equalization in a 50-Gb/s 25-km PAM4 IM/DD system...

Computationally-Efficient Sparsely-Connected Multi-Output Neural Networks for IM/DD System Equalization

Z Xu, S Dong, H Ji, JH Manton, W Shieh

Conference Proceedings  |  2022  |  Optics InfoBase Conference Papers

Low-Complexity Multi-Task Learning Aided Neural Networks for Equalization in Short-Reach Optical Interconnects

Zhaopeng Xu, Shuangyu Dong, Jonathan H Manton, William Shieh

Journal article  |  2022  |  JOURNAL OF LIGHTWAVE TECHNOLOGY

With the rapid development of machine learning technologies in recent years, different types of neural network (NN)-based equalize..

Non-Invasive Axle-Based Vehicle Classification Utilising Tracking Radar Technology

VRJ Deville, CM Lievers, JH Manton

Conference Proceedings  |  2022  |  2022 19th European Radar Conference, EuRAD 2022

This paper demonstrates the feasibility of using tracking radar technology to provide non-invasive axle-based vehicle classificati..

Riemannian barycentres of Gibbs distributions: new results on concentration and convexity in compact symmetric spaces

S Said, JH Manton

Journal article  |  2021  |  Information Geometry

The Riemannian barycentre (or Fréchet mean) is the workhorse of data analysis for data taking values in Riemannian manifolds. The ..

On Riemannian and non-Riemannian Optimisation, and Optimisation Geometry

Jeanne Lefevre, Florent Bouchard, Salem Said, Nicolas Le Bihan, Jonathan H Manton

Journal article  |  2021  |  IFAC PAPERSONLINE

Optimisation algorithms such as the Newton method were first generalised to manifolds bv generalising the components of the algori..

Hidden Markov chains and fields with observations in Riemannian manifolds

Salem Said, Nicolas Le Bihan, Jonathan H Manton

Journal article  |  2021  |  IFAC PAPERSONLINE

Hidden Markov chain, or Markov field, models, with observations in a Euclidean space, play a major role across signal and image pr..

Online Transfer Learning: Negative Transfer and Effect of Prior Knowledge

X Wu, JH Manton, U Aickelin, J Zhu

Conference Proceedings  |  2021  |  IEEE International Symposium on Information Theory: Proceedings

Transfer learning is a machine learning paradigm where the knowledge from one task is utilized to resolve the problem in a related..