no code implementations • 8 Oct 2023 • Fengpei Wang, Clarice Poon, Tony Shardlow
The use of optimal transport (OT) distances, and in particular entropic-regularised OT distances, is an increasingly popular evaluation metric in many areas of machine learning and data science.
no code implementations • 3 May 2022 • Clarice Poon, Gabriel Peyré
Our main theoretical contribution connects gradient descent on this reformulation to a mirror descent flow with a varying Hessian metric.
1 code implementation • NeurIPS 2021 • Clarice Poon, Gabriel Peyré
Iteratively reweighted least square (IRLS) is a popular approach to solve sparsity-enforcing regression problems in machine learning.
1 code implementation • 18 Jan 2021 • Jingwei Liang, Clarice Poon
In the realm of deterministic optimization, the sequence generated by iterative algorithms (such as proximal gradient descent) exhibit "finite activity identification", namely, they can identify the low-complexity structure in a finite number of iterations.
1 code implementation • 23 Nov 2020 • Mohammad Golbabaee, Clarice Poon
We propose a novel numerical approach to separate multiple tissue compartments in image voxels and to estimate quantitatively their nuclear magnetic resonance (NMR) properties and mixture fractions, given magnetic resonance fingerprinting (MRF) measurements.
no code implementations • 8 Nov 2019 • Clarice Poon, Gabriel Peyré
Our main contribution is a proof of a continuous counterpart to this result for the Blasso.
1 code implementation • 14 Feb 2019 • Vegard Antun, Francesco Renna, Clarice Poon, Ben Adcock, Anders C. Hansen
Deep learning, due to its unprecedented success in tasks such as image classification, has emerged as a new tool in image reconstruction with potential to change the field.
1 code implementation • ICML 2018 • Clarice Poon, Jingwei Liang, Carola Schoenlieb
In this paper, we present a local convergence anal- ysis for a class of stochastic optimisation meth- ods: the proximal variance reduced stochastic gradient methods, and mainly focus on SAGA (Defazio et al., 2014) and Prox-SVRG (Xiao & Zhang, 2014).