Grigorios Mingas
Imperial College London
14 Papers
57 Citations
Grigorios Mingas is an academic researcher from Imperial College London. The author has contributed to research in topics: Markov chain Monte Carlo & Computer science. The author has an hindex of 9, co-authored 12 publications. Previous affiliations of Grigorios Mingas include Aristotle University of Thessaloniki & The Turing Institute.
Chat about Author
Papers
Parallel resampling for particle filters on FPGAs
Shuanglong Liu,Grigorios Mingas,Christos-Savvas Bouganis +2 more
- 01 Dec 2014
TL;DR: Novel parallel architectures that map four state-of-the-art resampling algorithms (systematic, residual systematic, Metropolis and Rejection resamplings) to a FPGA to further optimize the performance of the above systems.
26
Parallel tempering MCMC acceleration using reconfigurable hardware
Grigorios Mingas,Christos-Savvas Bouganis +1 more
- 19 Mar 2012
TL;DR: A novel FPGA architecture to accelerate Parallel Tempering, a computationally expensive, popular MCMC method, which is designed to sample from multimodal distributions, and is robust to reductions in the arithmetic precision used to evaluate the sampling distribution, opening the way for the handling of previously intractable problems.
22
An exact MCMC accelerator under custom precision regimes
Shuanglong Liu,Grigorios Mingas,Christos-Savvas Bouganis +2 more
- 01 Dec 2015
TL;DR: A novel mixed precision MCMC accelerator for FPGAs is introduced, which simulates from the exact probability distribution in contrast to existing approximate MCMC samplers, and its performance is evaluated using two Bayesian logistic regression case studies of varying complexity.
19
Multilevel Delayed Acceptance MCMC
TL;DR: A novel Markov chain Monte Carlo method that exploits a hierarchy of models of increasing complexity to efficiently generate samples from an unnormalized target distribution is developed and shows that the algorithm satisfies detailed balance, hence is ergodic for the target distribution.
A Custom Precision Based Architecture for Accelerating Parallel Tempering MCMC on FPGAs without Introducing Sampling Error
Grigorios Mingas,Christos-Savvas Bouganis +1 more
- 29 Apr 2012
TL;DR: This work proposes a novel streaming FPGA architecture to accelerate Parallel Tempering, a widely adopted MCMC method designed to sample from multimodal distributions, and demonstrates how custom precision can be intelligently employed without introducing sampling errors.
13