OCITITCOMay 15

Towards Tsallis Fully Probabilistic Design

arXiv:2602.2389219.6
AI Analysis

For researchers in stochastic control and decision-making, this work extends FPD to handle heavy-tailed distributions, but the contribution is incremental as it applies a known divergence to an existing framework.

The paper generalizes the Fully Probabilistic Design (FPD) framework by replacing Kullback-Leibler divergence with Tsallis divergence, enabling modeling of non-Gaussian tail behavior. It provides a constructive proof of convergence via a double iteration scheme that asymptotically converges to an optimal solution.

Fully Probabilistic design (FPD) is a powerful framework offering an elegant and unifying account of stochastic control, learning and decision-making. Here we introduce a generalized FPD framework, which we term as Tsallis FPD. Tsallis FPD uses Tsallis divergence in place of the Kullback-Leibler divergence that defines the standard FPD cost term. Tsallis divergence is a natural generalization of the KL divergence, rooted in non-extensive statistical mechanics and providing flexibility towards modeling stochastic processes with non-Gaussian tail behavior. After formulating Tsallis FPD, we develop a constructive proof of convergence by formulating a fixed point iteration. The construction takes the form of a double iteration scheme that performs a sequence of backwards inductions, rather than a single pass down the stages that constitutes the proven approach for classical FPD. We prove that this construction asymptotically converges to a fixed point and that this fixed point is an optimal solution to Tsallis FPD.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes