The twenty-third session of the LSSTC DSFP focuses on Statistics and Bayesian Inference. The guest instructors for Session 23 are:
- Dr. Sylvia Biscoveanu (CIERA | Northwestern)
- Dr. Greg Gilbert (Caltech)
- Dr. Chad Schafer (Carnegie Mellon)
- Dr. Megan Newsome (University of Texas, Austin)
Lectures were also delivered by the DSFP leadership team:
- Dr. Adam Miller (CIERA | Northwestern)
- Dr. Bryan Scott (CIERA | Northwestern)
"Now Look to the future and claim the prize ahead."
~ Jacqueline M. Hughes-Oliver
--
Three orientation lectures are provided asynchronously, these are:
- A Brief Introduction to git/GitHub; B Scott
- Building Visualizations Via Principles of Design; A Miller
- Goals of the DSFP; A Miller
Sunday, May 18, 2025
- 10:30 AM - 11:00 AM Registration & Introductions
- 11:00 AM - 11:30 AM New Fellow Survey |
- 11:30 AM - 12:00 PM Introduction to the Vera C Rubin Observatory and Legacy Survey of Space & Time
- 12:00 PM - 1:00 PM LUNCH | Code of Conduct Discussion (TBD)
- 01:00 PM - 03:00 PM Overview of Supervised and Unsupervised Machine Learning
- 03:00 PM - ??? Break
"When the Facts Change, I change my mind. What do you do, sir?"
~ John Maynard Keynes (attributed)
--
Monday May 19, 2025
- 08:30 AM – 09:00 AM o Registration
- 09:00 AM – 09:45 AM o Meet the new cohort
- 09:45 AM – 10:30 AM o Introduction to Probability and its Applications, B Scott
- 10:30 AM – 11:00 AM o Break
- 11:00 AM – 12:00 PM o Problem| Solution: Introduction to Probability and its Applications, B Scott
- 12:00 PM – 01:30 PM o LUNCH
- 01:30 PM – 02:30 PM o Understanding Data, Optimization, and Classical Inference A Miller
- 02:30 PM – 03:30 PM o Problem | Solution: Optimization; A Miller
- 03:30 PM – 04:00 PM o Break
- 04:00 PM – 05:00 PM o Introduction to Intro Bayes; S Biscoveanu
- 05:00 PM – 06:00 PM o Problem | Solution: Intro Bayes; S Biscoveanu
- 07:00 PM - ??:?? PM o Group dinner
"It is a capital mistake to theorize before one has data. Insensibly one begins to twist facts to suit theories."
~ Sir Arthur Conan Doyle
--
Tuesday, May 20, 2025
- 09:00 AM - 10:30 AM o Problem | Solution Metroplis Hasting Sampling; A Miller
- 10:00 AM - 11:00 AM o Break
- 11:00 AM - 12:00 PM o Model Comparison and Misspecification; S Biscoveanu
- 12:00 PM - 01:30 PM o LUNCH
- 01:30 PM - 03:00 PM o Problem | Solution: Model Comparison and Misspecification; S Biscovenau
- 03:00 PM - 04:00 PM o Priors, Likelihoods, Posteriors, and all that; B Scott
- 04:00 PM - 04:30 PM o BREAK
- 04:30 PM - 05:30 PM o Problem | Solution: Priors, Likelihoods, Posteriors, and all that; B Scott
"A paradox is simply an error out of control; i.e. one that has trapped so many unwary minds that it has gone public, become institutionalized in our literature, and taught as truth."
~ ET Jaynes
--
Wednesday, May 21, 2025
- 09:00 AM – 09:45 AM o Hamiltonian, Nested, and Ensemble Sampling; G Gilbert
- 09:45 AM – 10:15 AM o Break
- 10:15 AM – 12:00 PM o Problem| Solutions: Hamiltonian, Nested, and Ensemble Sampling; G Gilbert
- 12:00 PM – ??:?? PM o BREAK
"All knowledge is, in final analysis, history. All sciences are, in the abstract, mathematics. All judgements are, in their rationale, statistics."
~ C.R. Rao
--
Thursday, May 23, 2025
- 09:00 AM – 10:00 AM o Probabilistic Graphical Models; C Schafer
- 10:00 AM – 10:30 AM o Break
- 10:30 AM – 12:00 PM o Problem: Solutions; Probabilistic Graphical Models; C Schafer
- 12:00 PM – 01:30 PM o LUNCH
- 01:30 PM – 02:30 PM o Hierarchical Modeling; G Gilbert
- 02:30 PM – 04:00 PM o Problem | Solution : Hierarchical Modeling; G Gilbert
- 04:00 PM – 04:30 PM o Break
- 04:30 PM – 05:00 PM o Hack Pitch Session
"It matters little who first arrives at an idea, rather what is significant is how far that idea can go."
~ Sophie Germain
--
Friday, May 24, 2025
- 9:00 AM - 9:45 AM o Intractable Posteriors; G Gilbert
- 09:45 AM – 10:45 AM o Problem Solution; Intractable Posteriors G Gilbert
- 10:45 AM – 11:00 AM o BREAK
- 11:00 AM – 12:00 PM o Hack Session
- 12:00 PM – 01:00 PM o LUNCH
- 01:00 PM – 04:30 PM o Hack Session
- 04:30 PM – 05:00 PM o Hack tag–up & Meeting wrap up