Search arXivSearch

arXiv · 2609.18992

From Optimal Transport to Optimal Quantization: A Variational Study of the Witsenhausen Counterexample

Abstract

We study the scalar Witsenhausen counterexample through optimal transport. Absorbing the first control into a transport map recasts the problem as the variational problem $J^=\inf_Q{k^2W_2^2(P,Q)+\operatorname{mmse}(Q)}$ over target laws $Q$. This formulation balances quadratic Wasserstein transport cost against minimum mean-square estimation error, with the optimal first controller recovered as the monotone rearrangement that pushes the prior $P$ to a minimizing law $Q^$. We establish existence and absolute continuity of $Q^$, derive an Euler-Lagrange condition, give an equivalent Fisher-information representation of the estimation cost, and obtain a semi-closed-form Gaussian benchmark with an explicit threshold for linear optimality. Restricting the target law to finite support yields an MMSE-regularized optimal quantization problem. Its stationarity conditions couple centroid levels with Voronoi decision cells and reduce to the classical Lloyd-Max conditions when control is expensive. We solve this nonconvex problem using a deterministic-annealing homotopy in the control penalty $k$. Finally, we derive the small- and large-$k$ asymptotics of $J^$ and identify the limiting controllers: a linear controller when control is expensive and a two-level signaling quantizer when it is cheap. Numerical results illustrate both regimes.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Quanyan Zhu. 2026-07-17. From Optimal Transport to Optimal Quantization: A Variational Study of the Witsenhausen Counterexample. https://arxiv.org/abs/2609.18992

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

Strategic Inference in Stackelberg Games: Optimal Control for Revealing Adversary Intent

We study a continuous-time stochastic Stackelberg game in which a leader seeks to accomplish a primary objective while inferring a hidden parameter of a rational follower. The follower solves an entropy-regularized linear-quadratic tracking problem and responds to the leader's trajectory with a randomized policy. Anticipating this response, the leader designs informative controls to maximize the estimation efficiency for the follower's latent intent, through maximum likelihood estimation. Unlike prior work on discrete-time or finite-candidate inverse learning, our framework enables continuous parameter inference without prior assumptions and endogenizes the information source through the follower's strategic feedback. We derive semi-explicit solutions, prove well-posedness, and develop recurrent neural network algorithms to approximate the leader's path-dependent control. Numerical experiments demonstrate how the leader balances task performance and information gain, highlighting the practical value of our approach for adversarial strategic inference.

math.OC

Stratification for Nonlinear Semidefinite Programming

This paper introduces a stratification framework for nonlinear semidefinite programming (NLSDP) that reveals and utilizes the geometry behind the nonsmooth KKT system. Based on the index stratification of $\mathbb{S}^n$ and its lift to the primal-dual space, a stratified variational analysis is developed. Specifically, we define the stratum-restricted regularity property, characterize it by the verifiable weak second order condition (W-SOC) and weak strict Robinson constraint qualification (W-SRCQ), and interpret the W-SRCQ geometrically via transversality, with stability along strata. The interactions of these properties across neighboring strata are further examined, leading to the conclusion that classical strong-form regularity conditions correspond to the local uniform validity of stratum-restricted counterparts. On the algorithmic side, a stratified Gauss--Newton method with normal steps and a correction mechanism is proposed for globally solving the KKT equation through a least-squares merit function. We demonstrate that the algorithm converges globally to directional stationary points. Moreover, under the second order sufficient condition (SOSC) and the strict Robinson constraint qualification (SRCQ) at an accumulation point, with a suitable correction threshold, the whole sequence converges superlinearly to this point, which is a KKT pair, and eventually identifies the active stratum. The rate is quadratic if the problem data are additionally of class $LC^2$ near the solution.

math.OC

Convergence Rate Analysis of SOAP with Arbitrary Orthogonal Projection Matrices

In this short note, we establish, for the first time, the convergence rate of SOAP, an efficient and popular matrix-based optimizer for training deep neural networks. Our analysis extends to a more general variant of SOAP that admits arbitrary orthogonal projection matrices and requires only that these matrices be conditionally independent of the current stochastic gradient at each iteration. For example, they may be constructed from information available up to the preceding step.

math.OC