A Deterministic Annealing Optimization Approach for Witsenhausen's and Related Decentralized Control Settings

TL;DR

This paper introduces a deterministic annealing optimization method for decentralized control problems, including a variant of Witsenhausen's counterexample with a side channel, demonstrating significant performance improvements over existing strategies.

Contribution

The paper extends deterministic annealing to a complex decentralized control setting with a side channel, achieving better strategies than prior affine and nonlinear approaches.

Findings

Deterministic annealing effectively finds complex control strategies.

The side channel enables significant performance gains.

The method outperforms traditional affine and nonlinear strategies.

Abstract

This paper studies the problem of mapping optimization in decentralized control problems. A global optimization algorithm is proposed based on the ideas of ``deterministic annealing" - a powerful non-convex optimization framework derived from information theoretic principles with analogies to statistical physics. The key idea is to randomize the mappings and control the Shannon entropy of the system during optimization. The entropy constraint is gradually relaxed in a deterministic annealing process while tracking the minimum, to obtain the ultimate deterministic mappings. Deterministic annealing has been successfully employed in several problems including clustering, vector quantization, regression, as well as the Witsenhausen's counterexample in our recent work[1]. We extend our method to a more involved setting, a variation of Witsenhausen's counterexample, where there is a side channel between the two controllers. The problem can be viewed as a two stage cancellation problem. We demonstrate that there exist complex strategies that can exploit the side channel efficiently, obtaining significant gains over the best affine and known non-linear strategies.