State encodings, not just the physical state, determine the collective synchronization outcomes of language-model agent populations, and the effect is model-family dependent.
Multiplayer Performative Prediction: Learning in Decision-Dependent Games
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Learning problems commonly exhibit an interesting feedback mechanism wherein the population data reacts to competing decision makers' actions. This paper formulates a new game theoretic framework for this phenomenon, called "multi-player performative prediction". We focus on two distinct solution concepts, namely (i) performatively stable equilibria and (ii) Nash equilibria of the game. The latter equilibria are arguably more informative, but can be found efficiently only when the game is monotone. We show that under mild assumptions, the performatively stable equilibria can be found efficiently by a variety of algorithms, including repeated retraining and the repeated (stochastic) gradient method. We then establish transparent sufficient conditions for strong monotonicity of the game and use them to develop algorithms for finding Nash equilibria. We investigate derivative free methods and adaptive gradient algorithms wherein each player alternates between learning a parametric description of their distribution and gradient steps on the empirical risk. Synthetic and semi-synthetic numerical experiments illustrate the results.
citation-role summary
citation-polarity summary
fields
physics.soc-ph 1years
2026 1verdicts
ACCEPT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Same physical state, different collective dynamics: state encodings select synchronization outcomes in language-model agents
State encodings, not just the physical state, determine the collective synchronization outcomes of language-model agent populations, and the effect is model-family dependent.