Bayes for scattering workshop
→
Europe/Zurich
M5 (COBIS)
M5
COBIS
Ole maaløes vej 3, Copenhagen
Registration
Participants
-
-
12:00
Lunch
-
Use cases for Bayes in scattering¶
- 1
-
2
Analysis of Small-Angle Scattering Data Using Model Fitting and Bayesian Regularization¶Speaker: Andreas Larsen (University of Copenhagen)
-
3
A simple bayesian method for 2D SANS¶Speaker: Alexander Holmes (European Spallation Source ERIC)
-
4
Bayes for reflectometry¶Speaker: Andrew McCluskey (Diamond Light Source)
-
5
Bayesian statistic for SAS and beyond¶
As a primer for discussion we will try to cover a few more SAS cases as well as other scattering techniques (particularly spectroscopy)
Speaker: Wojciech Potrzebowski (European Spallation Source ERIC)
-
Discussion¶
-
6
Break¶
-
7
Introduction¶
We will try out OST as at the NSS retreat
https://confluence.esss.lu.se/display/SD/Science+Retreat+2018+-+Fundamentals+of+OST
Think of topics before.
Ideas
Use cases
Workflow of data analysis
Presenting results
Computational techniques -
8
Group discussions¶
-
15:00
Coffee break
-
9
Group discussions¶
-
6
-
Wrap/up: Wrap-up¶
-
10
Report from discussions¶
Items discussed at the meeting:
- Bayesian statistics to optimize experiments i.e. when do I have good statistics to stop measuring?
- How to treat variables correlations
- Resolution functions for small angle scattering
- Bayesian model comparison (how to select good model for fitting)
- Bayesian statistics as way to avoid overfitting
- Bayesian statistics and its relation to machine and deep learning
- How to make scattering communities aware of Bayesian statistics: constant presentation, highlight important results, show probability distribution
- Plotting distributions, Library for plotting
- Easy accessible software
- Can we have a "community prior"?
- Data format for prior and posterior to update
-
11
Next steps¶
-
10
-
12:00