Pinned Repositories
GraphFilter-GraphSmoother
Graph Filter and Graph Smoother are algorithms for approximate filtering and smoothing in high-dimensional factorial hidden Markov models. The approximation involves discarding, in a principled way, likelihood factors according a notion of locality in a factor graph associated with the emission distribution.
HiddenMarkovNeuralNetwork
An hybrid between HMM and Neural networks for sequential training and time series forecasting
Multinomial-Approximations-for-compartmental-models
Explanation on how to use the Multinomial Approximations for compartmental models proposed in "Inference in Stochastic Epidemic Models via Multinomial Approximations" by N. Whiteley and L. Rimella
PAL
Fast and consistent inference in compartmental models of epidemics using Poisson Approximate Likelihoods
Optimal_IBM_proposal
Many epidemic models are naturally defined as individual-based models: where we track the state of each individual within a susceptible population. Inference for individual-based models is challenging due to the high-dimensional state-space of such models, which increases exponentially with population size. We consider sequential Monte Carlo algorithms for inference for individual-based epidemic models where we make direct observations of the state of a sample of individuals. Standard implementations, such as the bootstrap filter or the auxiliary particle filter are inefficient due to mismatch between the proposal distribution of the state and future observations. We develop new efficient proposal distributions that take account of future observations, leveraging the properties that (i) we can analytically calculate the optimal proposal distribution for a single individual given future observations and the future infection rate of that individual; and (ii) the dynamics of individuals are independent if we condition on their infection rates. Thus we construct estimates of the future infection rate for each individual, and then use an independent proposal for the state of each individual given this estimate. Empirical results show order of magnitude improvement in efficiency of the sequential Monte Carlo sampler for both SIS and SEIR models.
Build_Bayesian_NN_with_Pytorch
CV
epidemiology_workshop
GRDPG
Methodology Week 2
LorenzoRimella.github.io
LorenzoRimella's Repositories
LorenzoRimella/LorenzoRimella.github.io
LorenzoRimella/CV
LorenzoRimella/epidemiology_workshop
LorenzoRimella/SimBa-CL
Simulation Based Composite Likelihood
LorenzoRimella/PAL
Fast and consistent inference in compartmental models of epidemics using Poisson Approximate Likelihoods
LorenzoRimella/Build_Bayesian_NN_with_Pytorch
LorenzoRimella/GRDPG
Methodology Week 2
LorenzoRimella/SMC2-ILM
Stochastic modelling and parameters inference through SMC^2 for AMR bacteria
LorenzoRimella/Optimal_IBM_proposal
Many epidemic models are naturally defined as individual-based models: where we track the state of each individual within a susceptible population. Inference for individual-based models is challenging due to the high-dimensional state-space of such models, which increases exponentially with population size. We consider sequential Monte Carlo algorithms for inference for individual-based epidemic models where we make direct observations of the state of a sample of individuals. Standard implementations, such as the bootstrap filter or the auxiliary particle filter are inefficient due to mismatch between the proposal distribution of the state and future observations. We develop new efficient proposal distributions that take account of future observations, leveraging the properties that (i) we can analytically calculate the optimal proposal distribution for a single individual given future observations and the future infection rate of that individual; and (ii) the dynamics of individuals are independent if we condition on their infection rates. Thus we construct estimates of the future infection rate for each individual, and then use an independent proposal for the state of each individual given this estimate. Empirical results show order of magnitude improvement in efficiency of the sequential Monte Carlo sampler for both SIS and SEIR models.
LorenzoRimella/site_generator
LorenzoRimella/GraphFilter-GraphSmoother
Graph Filter and Graph Smoother are algorithms for approximate filtering and smoothing in high-dimensional factorial hidden Markov models. The approximation involves discarding, in a principled way, likelihood factors according a notion of locality in a factor graph associated with the emission distribution.
LorenzoRimella/HiddenMarkovNeuralNetwork
An hybrid between HMM and Neural networks for sequential training and time series forecasting
LorenzoRimella/Multinomial-Approximations-for-compartmental-models
Explanation on how to use the Multinomial Approximations for compartmental models proposed in "Inference in Stochastic Epidemic Models via Multinomial Approximations" by N. Whiteley and L. Rimella
LorenzoRimella/RGeode