DataScience@BI seminar with Joel Dryer

DataScience@BI seminar invites Senior Research Fellow Joel Dryer, Univeristy of Oxford to give a talk within the field of computational statistics and machine learning.

Abstract:

Computer simulations are used widely across scientific disciplines, often taking the form of stochastic black-box generative models that consume input parameters and produce a random output. In general for such models, no likelihood function is available, often due to the complexity of the simulators. Consequently, it is often convenient to adopt so-called likelihood-free or simulation-based inference methods that mimic conventional likelihood-based procedures using data simulated at different parameter values. While many such approaches exist for independent and identically distributed data, adapting these techniques to simulators that generate time-series data consisting of dependent data points can be challenging. In this talk, we will discuss how path signatures can be used to perform simulation-based parameter inference for time-series simulators with the use of path signatures. We will argue that signatures flexibly enable both approximate Bayesian and frequentist inference with time-series simulators of different kinds, with competitive empirical performance in a variety of benchmark experiments.

• Read more about the speaker
• Visit our website to read more about the Department of Data Science and Analytics

The DataScience@bi seminar is organised by the Department of Data Science and Analytics, BI Norwegian Business School.