## Neural Stochastic Dual Dynamic Programming

29 Sept 2021, 00:33 (modified: 15 Mar 2022, 20:14)ICLR 2022 PosterReaders: Everyone
Keywords: data-driven algorithm design, learning to optimize, multi-stage stochastic optimization, primal-dual dynamic programming
Abstract: Stochastic dual dynamic programming (SDDP) is a state-of-the-art method for solving multi-stage stochastic optimization, widely used for modeling real-world process optimization tasks. Unfortunately, SDDP has a worst-case complexity that scales exponentially in the number of decision variables, which severely limits applicability to only low dimensional problems. To overcome this limitation, we extend SDDP by introducing a trainable neural model that learns to map problem instances to a piece-wise linear value function within intrinsic low-dimension space, which is architected specifically to interact with a base SDDP solver, so that can accelerate optimization performance on new instances. The proposed Neural Stochastic Dual Dynamic Programming ($$\nu$$-SDDP) continually self-improves by solving successive problems. An empirical investigation demonstrates that $$\nu$$-SDDP can significantly reduce problem solving cost without sacrificing solution quality over competitors such as SDDP and reinforcement learning algorithms, across a range of synthetic and real-world process optimization problems.
One-sentence Summary: We proposed neural-SDDP pushing the frontier of multi-stage stochastic optimization solver towards practical problem size.
Supplementary Material: zip
14 Replies