skip to main content

Title: Learning for Robust Combinatorial Optimization: Algorithm and Application
Learning to optimize (L2O) has recently emerged as a promising approach to solving optimization problems by exploiting the strong prediction power of neural networks and offering lower runtime complexity than conventional solvers. While L2O has been applied to various problems, a crucial yet challenging class of problems — robust combinatorial optimization in the form of minimax optimization — have largely remained under-explored. In addition to the exponentially large decision space, a key challenge for robust combinatorial optimization lies in the inner optimization problem, which is typically non-convex and entangled with outer optimization. In this paper, we study robust combinatorial optimization and propose a novel learning-based optimizer, called LRCO (Learning for Robust Combinatorial Optimization), which quickly outputs a robust solution in the presence of uncertain context. LRCO leverages a pair of learning-based optimizers — one for the minimizer and the other for the maximizer — that use their respective objective functions as losses and can be trained without the need of labels for training problem instances. To evaluate the performance of LRCO, we perform simulations for the task offloading problem in vehicular edge computing. Our results highlight that LRCO can greatly reduce the worst-case cost and improve robustness, while having a very low runtime complexity.  more » « less
Award ID(s):
1910208 1551661
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
IEEE Conference on Computer Communications
Page Range / eLocation ID:
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. David Wipf (Ed.)
    Learning to optimize (L2O) is an emerging approach that leverages machine learning to develop optimization methods, aiming at reducing the laborious iterations of hand engineering. It automates the design of an optimization method based on its performance on a set of training problems. This data-driven procedure generates methods that can efficiently solve problems similar to those in training. In sharp contrast, the typical and traditional designs of optimization methods are theory-driven, so they obtain performance guarantees over the classes of problems specified by the theory. The difference makes L2O suitable for repeatedly solving a particular optimization problem over a specific distribution of data, while it typically fails on out-of-distribution problems. The practicality of L2O depends on the type of target optimization, the chosen architecture of the method to learn, and the training procedure. This new paradigm has motivated a community of researchers to explore L2O and report their findings. This article is poised to be the first comprehensive survey and benchmark of L2O for continuous optimization. We set up taxonomies, categorize existing works and research directions, present insights, and identify open challenges. We benchmarked many existing L2O approaches on a few representative optimization problems. For reproducible research and fair benchmarking purposes, we released our software implementation and data in the package Open-L2O at 
    more » « less
  2. Abstract In this paper, we present a decentralized approach based on a simple set of rules to schedule multi-robot cooperative additive manufacturing (AM). The results obtained using the decentralized approach are compared with those obtained from an optimization-based method, representing the class of centralized approaches for manufacturing scheduling. Two simulated case studies are conducted to evaluate the performance of both approaches in total makespan. In the first case, four rectangular bars of different dimensions from small to large are printed. Each bar is first divided into small subtasks (called chunks), and four robots are then assigned to cooperatively print the resulting chunks. The second case study focuses on testing geometric complexity, where four robots are used to print a mask stencil (an inverse stencil, not face covering). The result shows that the centralized approach provides a better solution (shorter makespan) compared to the decentralized approach for small-scale problems (i.e., a few robots and chunks). However, the gap between the solutions shrinks while the scale increases, and the decentralized approach outperforms the centralized approach for large-scale problems. Additionally, the runtime for the centralized approach increased by 39-fold for the extra-large problem (600 chunks and four robots) compared to the small-scale problem (20 chunks and four robots). In contrast, the runtime for the decentralized approach was not affected by the scale of the problem. Finally, a Monte-Carlo analysis was performed to evaluate the robustness of the centralized approach against uncertainties in AM. The result shows that the variations in the printing time of different robots can lead to a significant discrepancy between the generated plan and the actual implementation, thereby causing collisions between robots that should have not happened if there were no uncertainties. On the other hand, the decentralized approach is more robust because a collision-free schedule is generated in real-time. 
    more » « less
  3. Many machine learning problems can be abstracted in solving game theory formulations and boil down to optimizing nested objectives, such as generative adversarial networks (GANs) and multi-agent reinforcement learning. Solving these games requires finding their stable fixed points or Nash equilibrium. However, existing algorithms for solving games suffer from empirical instability, hence demanding heavy ad-hoc tuning in practice. To tackle these challenges, we resort to the emerging scheme of Learning to Optimize (L2O), which discovers problem-specific efficient optimization algorithms through data-driven training. Our customized L2O framework for differentiable game theory problems, dubbed “Learning to Play Games" (L2PG), seeks a stable fixed point solution, by predicting the fast update direction from the past trajectory, with a novel gradient stability-aware, sign-based loss function. We further incorporate curriculum learning and self-learning to strengthen the empirical training stability and generalization of L2PG. On test problems including quadratic games and GANs, L2PG can substantially accelerate the convergence, and demonstrates a remarkably more stable trajectory. Codes are available at 
    more » « less
  4. The offline pickup and delivery problem with time windows (PDPTW) is a classical combinatorial optimization problem in the transportation community, which has proven to be very challenging computationally. Due to the complexity of the problem, practical problem instances can be solved only via heuristics, which trade-off solution quality for computational tractability. Among the various heuristics, a common strategy is problem decomposition, that is, the reduction of a large-scale problem into a collection of smaller sub-problems, with spatial and temporal decompositions being two natural approaches. While spatial decomposition has been successful in certain settings, effective temporal decomposition has been challenging due to the difficulty of stitching together the sub-problem solutions across the decomposition boundaries. In this work, we introduce a novel temporal decomposition scheme for solving a class of PDPTWs that have narrow time windows, for which it is able to provide both fast and high-quality solutions. We utilize techniques that have been popularized recently in the context of online dial-a-ride problems along with the general idea of rolling horizon optimization. To the best of our knowledge, this is the first attempt to solve offline PDPTWs using such an approach. To show the performance and scalability of our framework, we use the optimization of paratransit services as a motivating example. Due to the lack of benchmark solvers similar to ours (i.e., temporal decomposition with an online solver), we compare our results with an offline heuristic algorithm using Google OR-Tools. In smaller problem instances (with an average of 129 requests per instance), the baseline approach is as competitive as our framework. However, in larger problem instances (approximately 2,500 requests per instance), our framework is more scalable and can provide good solutions to problem instances of varying degrees of difficulty, while the baseline algorithm often fails to find a feasible solution within comparable compute times. 
    more » « less
  5. null (Ed.)
    Simulated annealing is an effective and general means of optimization. It is in fact inspired by metallurgy, where the temperature of a material determines its behavior in thermodynamics. Likewise, in simulated annealing, the actions that the algorithm takes depend entirely on the value of a variable which captures the notion of temperature. Typically, simulated annealing starts with a high temperature, which makes the algorithm pretty unpredictable, and gradually cools the temperature down to become more stable. A key component that plays a crucial role in the performance of simulated annealing is the criteria under which the temperature changes namely, the cooling schedule. Motivated by this, we study the following question in this work: "Given enough samples to the instances of a specific class of optimization problems, can we design optimal (or approximately optimal) cooling schedules that minimize the runtime or maximize the success rate of the algorithm on average when the underlying problem is drawn uniformly at random from the same class?" We provide positive results both in terms of sample complexity and simulation complexity. For sample complexity, we show that O (m^1/2) samples suffice to find an approximately optimal cooling schedule of length m. We complement this result by giving a lower bound of Ω (m^1/3) on the sample complexity of any learning algorithm that provides an almost optimal cooling schedule. These results are general and rely on no assumption. For simulation complexity, however, we make additional assumptions to measure the success rate of an algorithm. To this end, we introduce the monotone stationary graph that models the performance of simulated annealing. Based on this model, we present polynomial time algorithms with provable guarantees for the learning problem. 
    more » « less