Regret Equals Covariance: A Closed-Form Characterization for Stochastic Optimization

TL;DR

This paper introduces a closed-form covariance-based formula for expected regret in stochastic optimization, significantly reducing computational complexity and enabling faster estimation compared to traditional simulation methods.

Contribution

It proves that regret equals covariance in certain problems and provides explicit bounds and estimators, improving efficiency and understanding of stochastic optimization.

Findings

Exact regret decomposition as covariance plus residual under certain conditions.

Covariance-based estimation is orders of magnitude faster than SAA.

Validated results on synthetic and real-world portfolio data.

Abstract

Regret is the cost of uncertainty in algorithmic decision-making. Quantifying regret typically requires computationally expensive simulation via Sample Average Approximation (SAA), with complexity $\mathcal{O}(Bn^{2}d^{3})$ in the number of scenarios $B$, variables $n$, and constraints $d$. % This paper proves that expected regret in any stochastic optimization problem admits the exact decomposition % \begin{equation*} \mathrm{Regret}(c) = \mathrm{Cov}(c,\,\pi^{*}(c)) + R(c), \end{equation*} % where $c$ is the vector of uncertain parameters, $\pi^{*}(c)$ is the optimal decision, and $R(c)$ is a residual whose magnitude we bound explicitly under Lipschitz, smooth, and strongly convex conditions. % For linear programs and unconstrained quadratic programs, including the classical Markowitz portfolio problem, we prove $R(c)=0$ exactly, so that $\mathrm{Regret}(c) = \mathrm{Cov}(c,\pi^{*}(c))$ holds without approximation. % When historical cost-decision pairs $\{(c_i, \pi^*(c_i))\}$ are available, the covariance can be estimated in $\mathcal{O}(nd^{2})$ time, which is orders of magnitude faster than SAA. The estimation is performed by a single pass through the data. % We derive concentration bounds, a central limit theorem, and an asymptotically unbiased residual estimator, and we validate all results on synthetic LP, QP, and integer programming instances and on a rolling-window portfolio experiment using ten years of CRSP equity data.