Marcelo Pereyra | Welcome

Maxwell Insitute for Mathematical Sciences
School of Mathematical and Computer Sciences, Heriot-Watt University

News

Workshop I am organising a workshop on “New mathematical methods in computational imaging”, at Heriot-Watt University in Edinburgh, 29 June 2017. For more details and to register please see the workshop webpage.

Talk I will be presenting my recent works Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreau and Maximum-a-posteriori estimation with Bayesian confidence regions at the Applied Inverse Problems conference, Hangzhou, 29 May - June 2 2017.

Talk I will be presenting Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreau at the SIAM Optimization Conference, Vancouver, 22-25 May 2017.

Talk I will be presenting my recent work Maximum-a-posteriori estimation with Bayesian confidence regions at the Maxwell Institute's Probability & Statistics day, Edinburgh, May 17 2017.

Talk I will give a talk on "Bayesian inference by convex optimisation" at the LMS/Turing workshop on Inverse Problems and Data Science Edinburgh, 8-10 May 2017.

Talk I will give a talk on "Bayesian inference by convex optimisation" at the CRISM statistics seminar series at the University of Warwick, March 3 2017.

Workshop I am organising a workshop on “Mathematical imaging with partially unknown models” with Carola Schönlieb and Martin Benning. The workshop will take place at Jesus College in Cambridge, 20-21 Feb. 2017. For more details and to register please see the workshop webpage.

Talk I will be presenting my recent work Revisiting maximum-a-posteriori estimation in log-concave models at the BASP Frontiers workshop.

Preprint I have posted a new preprint "Revisiting maximum-a-posteriori estimation in log-concave models: from differential geometry to decision theory". Please see https://arxiv.org/abs/1612.06149

Preprint Alain Durmus, Eric Moulines and I have posted a new preprint "Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreau". Please see https://arxiv.org/abs/1612.07471

New paper I am glad to report that "Maximum-a-posteriori estimation with Bayesian confidence regions" will soon appear in SIAM Journal on Imaging Sciences | http://arxiv.org/abs/1602.08590

New paper "Stroke Onset Time Determination Using MRI Relaxation Times without Non-Ischaemic Reference in A Rat Stroke Model" with T. Norton, M. Knight, B. Mcgarry, K. T. Jokivarsi, O. H. J. Grohn and R. Kauppinen will soon appear in Biomedical Spectroscopy and Imaging.

New paper I am glad to report that the paper "Fast unsupervised Bayesian image segmentation with adaptive spatial regularisation" with Steve McLaughlin will soon appear in IEEE Trans. Image Process | http://arxiv.org/abs/1502.01400

© 2017 Marcelo Pereyra
Template design by Andreas Viklund / Best hosted at www.svenskadomaner.se