A new PyTorch toolkit estimates contraction-on-average conditions in closed-loop AI-agent models to support fairness and robustness analysis.
Iterated Piecewise-Stationary Random Functions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Within the study of uncertain dynamical systems, iterated random functions are a key tool. There, one samples a family of functions according to a stationary distribution. Here, we introduce an extension, where one sample functions according to a time-varying distribution over the family of functions. For such iterated piecewise-stationary random functions on Polish spaces, we prove a number of results, including a bound on the tracking error.
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
humancompatible.interconnect: Testing Properties of Repeated Uses of Interconnections of AI Systems
A new PyTorch toolkit estimates contraction-on-average conditions in closed-loop AI-agent models to support fairness and robustness analysis.