Norwegian version of this page

SCROLLER - A Stochastic ContROL approach to machine Learning with applications to Environmental Risk models

Image may contain: Font, Electric blue, Logo.

About the project

The main idea of ​​the SCROLLER project is to study the connections between stochastic analysis, risk theory and machine learning.

Stochastic analysis is the mathematical study of uncertainty over time. In particular, stochastic optimal control theory is a tool for making optimal decisions over time under uncertainty. The reason for working with stochastic models, as opposed to deterministic ones, is that most real-life problems are influenced by uncertain factors. Weather, politics, climate change and human actions are potential sources of uncertainty.

During the last decade, there has been a vast technological development and growth in computational power. In addition, digitization implies that
big data is available in many different settings. Machine learning is a set of mathematical algorithms and techniques which enable computers to improve at performing tasks with experience. Examples of ML algorithms are neural networks and reinforcement learning.

Machine learning algorithms can lead to wrong conclusions if we are
not careful in understanding the underlying mathematics. Though the experimental results of machine learning are good, there is still a lack of understanding of the mathematical reasons for these results. In particular, the literature concerning the connections between machine learning and stochastic analysis is sparse. The main purpose of the SCROLLER project is to study these connections.

In choice of applications throughout the SCROLLER project, we will focus on problems related to environmental and climate risks. For instance, we
will work on degradation models with respect to environmental risk factors. We will use environmental contours for safer risk assessment of structures exposed to extreme environmental events. Due to climate change, there is more extreme weather, and in general more uncertainty regarding the future. We hope that this project can contribute to derive suitable risk assessments which take this change into account.

Financing

This project is funded by the  Reseach Council of Norway . Funding ID: 299897

 

Publications

  • Agrell, Christian & Dahl, Kristina Rognlien (2021). Sequential Bayesian optimal experimental design for structural reliability analysis. Statistics and computing . ISSN 0960-3174.  31  . doi:  10.1007 / s11222-021-10000-2  Full text in knowledge archive .
  • Dahl, Kristina Rognlien & Eyjolfsson, Heidar (2021). Self-exciting jump processes as deterioration models, to be published in Proceedings of the 31st European Safety and Reliability Conference. Edited by B. Castanier, M. Cepin, D. Bigaud & C. Berenguer, Research Publishing, Singapore, ISBN: 981-973-0000-00-0. doi: 10.3850 / 981-973-0000-00-0.
  • Savku E. (2021). Fundamentals of Market Making via Stochastic Optimal Control, (Book Chapter) Submitted.
  • Christian Agrell & Kristina Rognlien Dahl (2021). Sequential Bayesian optimal experimental design for structural reliability analysis. Statistics and computing.  ISSN 0960-3174.  31
  • Kristina Rognlien Dahl & Arne Huseby (2020). Environmental contours and optimal design, In Piero Baraldi; Enrico Zio & Francesco P. Di Maio (ed.),  e-proceedings of the 30th European Safety and Reliability Conference and 15th Probabilistic Safety Assessment and Management Conference (ESREL2020 PSAM15).  Research Publishing Services.  ISBN 9789811485930.  3647.
  • Kristina Rognlien Dahl (2020). Forward-backward stochastic differential equation games with delay and noisy memory. Stochastic Analysis and Applications.  ISSN 0736-2994.  38, s 708- 729

View all works in Cristin

  • Emel Savku (2021). Stochastic Differential Games within the framework of Regime-Switches.
  • Emel Savku (2021). Portfolio Strategies via Stochastic Differential Games with Regimes.
  • Kristina Rognlien Dahl (2020). FBSDE games with delay & noisy memory.
  • Kristina Rognlien Dahl (2020). The SCROLLER project A Stochastic ContROL approach to machine Learning with applications to Environmental Risk models.
  • Kristina Rognlien Dahl (2020). The SCROLLER project and a subproject: Optimal design.
  • Kristina Rognlien Dahl & Arne Huseby (2020). Environmental contours and optimal design.

View all works in Cristin

Tags: Stochastics. Stochastic optimal control. Machine learning. Environmental applications.
Published Sep. 4, 2020 10:49 AM - Last modified June 10, 2021 3:17 PM