Brag Meeting 26th October 2017

When: Thursday 26th October 2017, 13:00-14:00.

Location: GP-Y801.

Included in meeting: 

This week we will have two presentations by Anthony and Daniel.  Details on their presentations are:

Anthony’s talk: Title: Fast and Likelihood-Free Parameter Estimation for Dynamic Queueing Networks

Important real-world systems such as airport terminals, manufacturing processes and hospitals are modeled with networks of queues. To estimate parameters, restrictive assumptions are placed on these models. For instance arrival and service distributions are assumed to be time-invariant. Violating this assumption are so-called Dynamic Queueing Networks (DQN) which are more realistic but do not allow for likelihood-based parameter estimation.

We consider the problem of using data to estimate the parameters of a DQN. We combine computationally efficient simulation with Queue Departure Computation (QDC) with Approximate Bayesian Computation (ABC) and Maximum Mean Discrepancy (MMD). DQNs are simulated in a computationally efficient manner with Queue Departure Computation (QDC), without the need for restrictive time-invariance assumptions. Parameters are inferred from data without any data-collection requirements, as is usual in queueing parameter inference. “

Daniel’s talk: Title: A probabilistic model-based approach for cell-type level effects in heterogeneous data

Epigenome-wide association studies are often performed using heterogeneous methylation samples, especially when there is no prior information as to which cell-types are disease-associated. In this talk I introduce a Bayesian model-based approach for making cell-type specific inferences in heterogeneous settings, by utilising a logistic transform to properly constrain parameters, and incorporating a prior knowledge of cell-type lineage via prior covariance structure. The approach was applied to the determination of cell-type-specific effects of sex in methylation, where cell-type information was present as an independent verification of the results. I also outline current and future work on this problem including the generalisation of this approach to other data-types.”

We look forward to seeing you all there!

Best regards,

Shovanur and Matt




Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s