# socx: GPU-Accelerated Chance-Constrained Stochastic Optimal Control using JAX

**Authors:** Tanmay Dokania, Yashwanth Kumar Nakka  
**Published:** 29 Oct 2026  
**Links:** [arXiv](https://arxiv.org/abs/2610.40427) · [PDF](https://arxiv.org/pdf/2610.40427) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2610.40427.html)

## Key numbers

- **98×**: …quadrotor and show a speed-up of up to 98× over MOSEK and up to 2224× over…
- **2224×**: …up to 98× over MOSEK and up to 2224× over SCS. socx also solves horizons up…

## Abstract

In this article, we present socx, a GPU-accelerated solver for lifted convex reformulations of linear stochastic optimal control under chance constraints, implemented in JAX. We demonstrate that by exploiting the sparse and independent structure of the problem, distributed optimization can reduce it to simpler problems: independent linear-quadratic tracking (LQT) problems and Euclidean projections onto sets. These simpler problems can be solved in parallel and then coupled using the constraints. To validate our solver, we run it on a hover-linearized 3D quadrotor and show a speed-up of up to 98× over MOSEK and up to 2224× over SCS. socx also solves horizons up to $N=1120$, whereas MOSEK runs out of memory at $N=320$. We present ablations to isolate the key components that enable the speed-up.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.