arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.01565math.OCcs.AI
收藏

Deep FlexQP:通过深度展开实现非线性规划的加速

Deep FlexQP: Accelerated Nonlinear Programming via Deep Unfolding

Georgia Institute of Technology(佐治亚理工学院);Massachusetts Institute of Technology(麻省理工学院)

Alex Oshin, Rahul Vodeb Ghosh, Augustinos D. Saravanos, Evangelos A. Theodorou

AI总结:

Deep FlexQP通过深度展开学习反馈策略,实现加速的非线性规划求解,优于现有方法并在多个基准测试中表现优异。

摘要:

我们提出了FlexQP,一种基于QP约束的$\ell_1$弹性松弛的始终可行的凸二次规划(QP)求解器。如果原始约束是可行的,FlexQP可以证明恢复最优解。如果约束不可行,FlexQP会找到一个最小化约束违反同时保持违反约束数量稀疏的解。这种不可行性自然出现在序列二次规划(SQP)子问题中,由于约束的线性化。我们在较弱的 coercivity 假设下证明了FlexQP的收敛性,使其在可行和不可行的QP中都具有鲁棒性。随后,我们应用深度展开来学习基于LSTM的、维度无关的反馈策略,用于算法参数,从而得到加速的Deep FlexQP。为了保持松弛的精确性保证,我们提出了一种归一化的训练损失,该损失结合了拉格朗日乘数。我们还设计了一种对数尺度的损失,用于PAC-Bayes泛化界限,从而获得更紧的性能证书,我们用它来构建具有保证QP子问题性能的加速SQP求解器。Deep FlexQP在一系列基准测试中优于最先进的学习QP求解器,包括投资组合优化、分类和回归问题,并通过微调扩展到具有超过10k变量和约束的密集QP。当部署在SQP中时,我们的方法在非线性轨迹优化问题上比使用OSQP的SQP快4-16倍,同时显著提高成功率。在预测安全过滤问题中,Deep FlexQP相比现有方法减少了超过70%的安全违规,并增加了43%的任务完成率。

英文摘要:

We propose FlexQP, an always-feasible convex quadratic programming (QP) solver based on an $\ell_1$ elastic relaxation of the QP constraints. If the original constraints are feasible, FlexQP provably recovers the optimal solution. If the constraints are infeasible, FlexQP identifies a solution that minimizes the constraint violation while keeping the number of violated constraints sparse. Such infeasibilities arise naturally in sequential quadratic programming (SQP) subproblems due to the linearization of the constraints. We prove the convergence of FlexQP under mild coercivity assumptions, making it robust to both feasible and infeasible QPs. We then apply deep unfolding to learn LSTM-based, dimension-agnostic feedback policies for the algorithm parameters, yielding an accelerated Deep FlexQP. To preserve the exactness guarantees of the relaxation, we propose a normalized training loss that incorporates the Lagrange multipliers. We additionally design a log-scaled loss for PAC-Bayes generalization bounds that yields substantially tighter performance certificates, which we use to construct an accelerated SQP solver with guaranteed QP subproblem performance. Deep FlexQP outperforms state-of-the-art learned QP solvers on a suite of benchmarks including portfolio optimization, classification, and regression problems, and scales to dense QPs with over 10k variables and constraints via fine-tuning. When deployed within SQP, our approach solves nonlinear trajectory optimization problems 4-16x faster than SQP with OSQP while substantially improving success rates. On predictive safety filter problems, Deep FlexQP reduces safety violations by over 70\% and increases task completion by 43\% compared to existing methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑