An unexpected connection between Bayes $A-$optimal designs and the Group Lasso

TL;DR

This paper reveals a novel connection between $A$-optimal design problems and group lasso regularization, enabling new scalable algorithms with proven convergence for large-scale experimental design tasks.

Contribution

It establishes an equivalence between $A$-optimal design and a regularized matrix optimization problem, leading to innovative algorithms with convergence guarantees.

Findings

Algorithms outperform existing methods on synthetic benchmarks.

Proposed methods have rigorous convergence guarantees.

Effective for large-scale $A$-optimal design problems.

Abstract

We show that the $A$-optimal design optimization problem over $m$ design points in $\mathbb{R}^n$ is equivalent to minimizing a quadratic function plus a group lasso sparsity inducing term over $n\times m$ real matrices. This observation allows to describe several new algorithms for $A$-optimal design based on splitting and block coordinate decomposition. These techniques are well known and proved powerful to treat large scale problems in machine learning and signal processing communities. The proposed algorithms come with rigorous convergence guaranties and convergence rate estimate stemming from the optimization literature. Performances are illustrated on synthetic benchmarks and compared to existing methods for solving the optimal design problem.