# An Adaptive Sampling Augmented Lagrangian Method for Stochastic Optimization with Deterministic Constraints

arXiv: https://arxiv.org/abs/2305.01018 · HTML: https://mlsanity.com/paper/2305.01018/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2023.

## Built on by (most cited first, 5 of 5)

- [AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods](https://mlsanity.com/paper/2402.11215/) (2024)
- [Trust-Region Sequential Quadratic Programming for Stochastic Optimization with Random Models](https://mlsanity.com/paper/2409.15734/) (2024)
- [High Probability Complexity Bounds of Trust-Region Stochastic Sequential Quadratic Programming with Heavy-Tailed Noise](https://mlsanity.com/paper/2503.19091/) (2025)
- [humancompatible.train: Implementing Optimization Algorithms for Stochastically-Constrained Stochastic Optimization Problems](https://mlsanity.com/paper/2509.21254/) (2025)
- [Benchmarking Stochastic Approximation Algorithms for Fairness-Constrained Training of Deep Neural Networks](https://mlsanity.com/paper/2507.04033/) (2025)

## Abstract (arXiv)

The primary goal of this paper is to provide an efficient solution algorithm based on the augmented Lagrangian framework for optimization problems with a stochastic objective function and deterministic constraints. Our main contribution is combining the augmented Lagrangian framework with adaptive sampling, resulting in an efficient optimization methodology validated with practical examples. To achieve the presented efficiency, we consider inexact solutions for the augmented Lagrangian subproblems, and through an adaptive sampling mechanism, we control the variance in the gradient estimates. Furthermore, we analyze the theoretical performance of the proposed scheme by showing equivalence to a gradient descent algorithm on a Moreau envelope function, and we prove sublinear convergence for convex objectives and linear convergence for strongly convex objectives with affine equality constraints. The worst-case sample complexity of the resulting algorithm, for an arbitrary choice of penalty parameter in the augmented Lagrangian function, is O(ε-3-δ), where ε > 0 is the expected error of the solution and δ > 0 is a user-defined parameter. If the penalty parameter is chosen to be O(ε-1), we demonstrate that the result can be improved to O(ε-2), which is competitive with the other methods employed in the literature. Moreover, if the objective function is strongly convex with affine equality constraints, we obtain O(ε-1log(1/ε)) complexity. Finally, we empirically verify the performance of our adaptive sampling augmented Lagrangian framework in machine learning optimization and engineering design problems, including topology optimization of a heat sink with environmental uncertainty.