A Note on a Possible Connection between Pontryagin Maximum Principle and Jaynes Maximum Entropy

The Pontryagin Maximum Principle

Theorem (PontryaginMaximum Principle). Suppose a final time T and controlstate pair (û, x̂) on [τ, T ] give the minimum in the problem above; assume that û is piecewise continuous. Then there exist a vector of Lagrange multipliers (λ0, λ) ∈ R × R with λ0 ≥ 0 and a piecewise smooth function p: [τ, T ] → R n such that the function ĥ(t) def =H(t, x̂(t), p(t), û(t)) is piecewise smooth, and one has ̇̂ ...

A Note on the Bivariate Maximum Entropy Modeling

Let X=(X1 ,X2 ) be a continuous random vector. Under the assumption that the marginal distributions of X1 and X2 are given, we develop models for vector X when there is partial information about the dependence structure between X1  and X2. The models which are obtained based on well-known Principle of Maximum Entropy are called the maximum entropy (ME) mo...

The Maximum Principle of Pontryagin

Independent Component Analysis Using Jaynes’ Maximum Entropy Principle

ICA deals with finding linear projections in the input space along which the data shows most independence. Therefore, mutual information between the projected outputs, which are usually called the separated outputs due to links with blind source separation (BSS), is considered to be a natural criterion for ICA. Minimization of the mutual information requires primarily the estimation of this qua...

Mean-Field Pontryagin Maximum Principle

We derive a Maximum Principle for optimal control problems with constraints given by the coupling of a system of ODEs and a PDE of Vlasov-type. Such problems arise naturally as Γ-limits of optimal control problems subject to ODE constraints, modeling, for instance, external interventions on crowd dynamics. We obtain these first-order optimality conditions in the form of Hamiltonian flows in the...