QLS Seminar - Thu. 26 June at 11h00 - "Non-Equilibrium Statistical Mechanics of/for AI" by Michael Chertkov (University of Arizona)

[Quantitative Life Sciences]

Dear All,

On Thursday, 26 June at 11:00 CET, Prof. Michael Chertkov (University of 
Arizona) will give a seminar titled:

*"**Non-Equilibrium Statistical Mechanics of/for AI**"

*_Abstract:

_

This talk presents a unifying applied mathematics/theoretical physics 
framework that bridges core components of modern generative AI -- 
diffusion models, reinforcement learning, and transformers -- through 
the lens of contemporary applied mathematics. Central to this framework 
are the concepts of /Decision Flows/ and /Path Integral Diffusions/, 
which offer structured approaches to sequential sampling over discrete, 
continuous, and hybrid spaces. These approaches are rooted in 
Green-function-based control, Schrödinger bridges, and non-equilibrium 
statistical physics.____

Building on recent work, we explore analytically tractable and 
algorithmically efficient regimes -- often requiring minimal use of 
neural networks -- where sampling from complex distributions becomes 
both explainable and extrapolative. We highlight connections between 
score-based diffusion, linearly-solvable Markov Decision Processes, and 
energy-based models, including emerging insights into phase transitions 
in generative AI (e.g., memorization and speciation dynamics).____

Applications span inference/sampling in Ising models, CIFAR-10 image 
generation, physics-informed reinforcement learning in turbulent flows, 
and auto-regressive modeling of statistical hydrodynamics. We also touch 
on decision-making under uncertainty in energy systems.

*
The seminar will take place in the _Common area, Old SISSA building, 
second floor - Via Beirut, 2__
_
* You are all most welcome to attend!

Best regards,
Erica

Erica Sarnataro
Group Secretary
Quantitative Life Sciences
The Abdus Salam International Centre for Theoretical Physics (ICTP)
Trieste,  Italy
Tel. +39-040-2240623
www.ictp.it/research/qls.aspx
e-mail:qls at ictp.it