Workshop on Neural Simulation-Based Inference (Day One)

— 5:00pm

Speaker:
Presented by: CMU Statistical Methods for the Physical Sciences Research Center

The  STAtistical Methods for the Physical Sciences (STAMPS@CMU) research center is organizing a weekend workshop on neural simulation-based inference on 4-5 October 2025. The workshop will take place in person at the CMU campus in Pittsburgh.  A webcast for remote participants will also be available.

Neural simulation-based inference (neural SBI) has led to a recent paradigm shift in statistical inference across fields ranging from astronomy and particle physics to climate and environmental science. The goal of this workshop is to bring together researchers in neural SBI who have so far been largely siloed within disjoint communities. We expect that this will lead to cross-pollination of ideas across these communities to facilitate the next advances in neural SBI and its applications.

The workshop will feature talks by leading researchers in neural SBI, poster contributions by junior researchers, and plenty of opportunities for interaction between the participants.

Confirmed speakers include

  • Kyle Cranmer (University of Wisconsin-Madison)
  • Gaia Grosso (Massachusetts Institute of Technology)
  • Patrick Heimbach (University of Texas at Austin)
  • Lukas Heinrich (Technical University of Munich)
  • Brian Nord (Fermilab)
  • Laurence Perreault-Levasseur (University of Montreal)
  • Barnabas Poczos (Carnegie Mellon University)
  • Brian Reich (North Carolina State University)
  • Bingjie Wang (Pennsylvania State University)
  • Larry Wasserman (Carnegie Mellon University)
  • Minge Xie (Rutgers University)
  • Andrew Zammit-Mangion (University of Wollongong)

REGISTER
→ Seats are limited so please register as soon as possible.

  • Poster Submissions deadline: September 26
  • In-Person Registration cutoff:  September 26
  • Remote Registration cutoff:  October 1

—

STAMPS@CMU develops foundational statistical methodology that addresses emerging open problems in fundamental physics, environmental and climate sciences. Our goal is to promote trustworthy scientific discovery that advances science and informs policy decisions. We achieve this by fostering mutually beneficial and sustained collaborations between data scientists and physical scientists to leverage scientific expertise, build trust in interpretable methods, and transfer knowledge across the mathematical and physical sciences. 
 

For More Information:
tsukiant@andrew.cmu.edu

Add event to Google
Add event to iCal