Flexible Differentiable Optimization via Model Transformations
Flexible Differentiable Optimization via Model Transformations
复制标题
通过模型转换进行灵活的可微分优化
DOI：
--
复制
发表时间：
2022
影响因子：
2.1
通讯作者：
B. Legat
中科院分区：
文献类型：
--
作者：
Akshay Sharma;Mathieu Besançon;J. Garcia;B. Legat
我们引入了DiffOpt.jl，这是一个Julia库，用于通过关于目标和/或约束中存在的任意参数的优化问题的解决方案进行区分。该库构建在MathOptInterface之上，从而利用了丰富的求解器生态系统，并与JUMP等建模语言很好地结合在一起。DiffOpt提供正向和反向差异化模式，支持从超参数优化到反向传播和敏感度分析的多种用例，将受限优化与端到端可区分编程连接起来。DiffOpt建立在区分二次规划和二次规划标准型的两条已知规则上。然而，由于其通过模型变换来区分的能力，用户不限于这些形式，并且可以关于可被重新表述为这些标准形式的任何模型的参数来区分。这特别包括混合仿射二次约束和凸二次约束或目标函数的程序。历史：被软件工具区域编辑Ted Ralphs接受。资助：A.Sharma在DiffOpt.jl上的工作是由谷歌代码之夏项目通过NumFocus资助的。M.Besançon通过德国联邦教育和研究部资助的研究校园模式[补助金05M14ZAM，05M20ZBM]得到部分支持。J·迪亚斯·加西亚的部分资金得到了巴西国家银行(CAPES)--财务代码001的支持。B.Legat得到了BAEF博士后奖学金、美国国家科学基金会[Grant OAC-1835443]和ERC Adv.[赠款885682]。补充材料：支持本研究结果的软件可在该文件及其补充资料(https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0283)以及IJOC GitHub软件储存库(https://github.com/INFORMSJoC/2022.0283)中获得。完整的IJOC软件和数据存储库可在https://informsjoc.github.io/上找到。
We introduce DiffOpt.jl, a Julia library to differentiate through the solution of optimization problems with respect to arbitrary parameters present in the objective and/or constraints. The library builds upon MathOptInterface, thus leveraging the rich ecosystem of solvers and composing well with modeling languages like JuMP. DiffOpt offers both forward and reverse differentiation modes, enabling multiple use cases from hyperparameter optimization to backpropagation and sensitivity analysis, bridging constrained optimization with end-to-end differentiable programming. DiffOpt is built on two known rules for differentiating quadratic programming and conic programming standard forms. However, thanks to its ability to differentiate through model transformations, the user is not limited to these forms and can differentiate with respect to the parameters of any model that can be reformulated into these standard forms. This notably includes programs mixing affine conic constraints and convex quadratic constraints or objective function. History: Accepted by Ted Ralphs, Area Editor for Software Tools. Funding: The work of A. Sharma on DiffOpt.jl was funded by the Google Summer of Code program through NumFocus. M. Besançon was partially supported through the Research Campus Modal funded by the German Federal Ministry of Education and Research [Grant 05M14ZAM, 05M20ZBM]. J. Dias Garcia was supported in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior – Brasil (CAPES) – Finance Code 001. B. Legat was supported by a BAEF Postdoctoral Fellowship, the NSF [Grant OAC-1835443], and the ERC Adv. [Grant 885682]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0283 ), as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2022.0283 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .
DOI：
10.1287/ijoc.2021.1067
发表时间：
2020-02
期刊：
INFORMS J. Comput.
影响因子：
--
作者：
B. Legat;O. Dowson;J. Garcia;Miles Lubin
通讯作者：
B. Legat;O. Dowson;J. Garcia;Miles Lubin