5 papers
Theory of collective learning in populations of adaptive agents
Gerhard Jung, Johann Asnacios, Misaki Ozawa +2
We investigate homogeneous populations of smart active agents that exchange information with their neighbors to perform a decentralized learning process aimed at achieving a prescr…
The limits of interpretability in multiple linear regression
Anand Sharma, Chen Liu, Daniele Coslovich +1
Interpreting machine-learning models has attracted increasing attention, particularly in the physical sciences, where one often seeks to understand the underlying mechanisms rather…
Entropy of Liquids and Glasses from Recurring Structural Patterns
Nina Javerzat, Gerhard Jung, Jorge Kurchan +1
We compute the low-temperature configurational entropy of a two-dimensional supercooled liquid. Our method, based on a higher-dimensional version of the Grassberger--Procaccia algo…
Rényi complexity in mean-field disordered systems
Nina Javerzat, Eric Bertin, Misaki Ozawa
Configurational entropy, or complexity, plays a critical role in characterizing disordered systems such as glasses, yet its measurement often requires significant computational res…
Kinetic theory of decentralized learning for smart active matter
Gerhard Jung, Misaki Ozawa, Eric Bertin
Smart active matter has the ability to control its motion guided by individual policies to achieve collective goals. We introduce a theoretical framework to study a decentralized l…