# A single cut proximal bundle method for stochastic convex composite optimization

arXiv: https://arxiv.org/abs/2207.09024 · HTML: https://mlsanity.com/paper/2207.09024/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2022.

## Built on by (most cited first, 4 of 4)

- [Proximal Oracles for Optimization and Sampling](https://mlsanity.com/paper/2404.02239/) (2024)
- [Accelerated stochastic first-order method for convex optimization under heavy-tailed noise](https://mlsanity.com/paper/2510.11676/) (2025)
- [Variance Reduction and Low Sample Complexity in Stochastic Optimization via Proximal Point Method](https://mlsanity.com/paper/2402.08992/) (2024)
- [Bias-Variance Trade-off for Clipped Stochastic First-Order Methods: From Bounded Variance to Infinite Mean](https://mlsanity.com/paper/2512.14686/) (2025)

## Abstract (arXiv)

This paper considers optimization problems where the objective is the sum of a function given by an expectation and a closed convex composite function, and proposes stochastic composite proximal bundle (SCPB) methods for solving it. Complexity guarantees are established for them without requiring knowledge of parameters associated with the problem instance. Moreover, it is shown that they have optimal complexity when these problem parameters are known. To the best of our knowledge, this is the first proximal bundle method for stochastic programming able to deal with continuous distributions. Finally, we present computational results showing that SCPB substantially outperforms the robust stochastic approximation (RSA) method in all instances considered.