Publication type: Lecture
Title: Boosting parameter inference with stochastic models using molecular dynamics and high-performance computing
Authors: Ulzega, Simone
Issue Date: 11-Apr-2017
Language: English
Subject (DDC): 003: Systems
Abstract: Parameter inference is a fundamental problem in data-driven modeling. The aim is to find a so-called posterior distribution of model parameters that are able to explain observed data and can be used for making probabilistic predictions. We propose a novel, exact, very efficient and highly parallelizable Hamiltonian Monte Carlo approach for generating posterior parameter distributions, for stochastic models calibrated to measured time-series. The algorithm is inspired by re-interpreting the posterior distribution as a statistical mechanics partition function of an object akin to a polymer, whose dynamics is confined by both the model and the measurements.
Further description: Invited seminar at ENS, Paris
License (according to publishing contract): Not specified
Departement: Life Sciences and Facility Management
Organisational Unit: Institute of Computational Life Sciences (ICLS)
Appears in collections:Publikationen Life Sciences und Facility Management

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.