2023-04-11-bae23a.md

title	software	abstract	section	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Deep Value Function Networks for Large-Scale Multistage Stochastic Programs	https://github.com/HyunglipBae/DVFN	A neural networks-based stagewise decomposition algorithm called Deep Value Function Networks (DVFN) is proposed for large-scale multistage stochastic programming (MSP) problems. Traditional approaches such as nested Benders decomposition and its stochastic variant, stochastic dual dynamic programming (SDDP) approximates value functions as piecewise linear convex functions by gradually accumulating subgradient cuts from dual solutions of stagewise subproblems. Although they have been proven effective for linear problems, nonlinear problems may suffer from the increasing number of subgradient cuts as they proceed. A recently developed algorithm called Value Function Gradient Learning (VFGL) replaced the piecewise linear approximation with parametric function approximation, but its performance heavily depends upon the choice of parametric forms like most of traditional parametric machine learning algorithms did. On the other hand, DVFN approximates value functions using neural networks, which are known to have huge capacity in terms of their functional representations. The art of choosing appropriate parametric form becomes a simple labor of hyperparameter search for neural networks. However, neural networks are non-convex in general, and it would make the learning process unstable. We resolve this issue by using input convex neural networks that guarantee convexity with respect to inputs. We compare DVFN with SDDP and VFGL for solving large-scale linear and nonlinear MSP problems: production optimization and energy planning. Numerical examples clearly indicate that DVFN provide accurate and computationally efficient solutions.	Regular Papers	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	bae23a	0	Deep Value Function Networks for Large-Scale Multistage Stochastic Programs	11267	11287	11267-11287	11267	false	Bae, Hyunglip and Lee, Jinkyu and Chang Kim, Woo and Lee, Yongjae	given family Hyunglip Bae given family Jinkyu Lee given family Woo Chang Kim given family Yongjae Lee	2023-04-11		Proceedings of The 26th International Conference on Artificial Intelligence and Statistics	206	inproceedings	date-parts 2023 4 11	https://proceedings.mlr.press/v206/bae23a/bae23a.pdf