PyTorchKR Papers

최신 논문

총 1,512편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2112.11534

Noise-injected analog Ising machines enable ultrafast statistical sampling and machine learning

Ising machines are a promising non-von-Neumann computational concept for neural network training and combinatorial optimization. However, while various neural networks can be implemented with Ising machines, their inability to perform fast statistical sampling makes them inefficient for training neural networks compared to digital computers. Here, we introduce a universal concept to achieve ultrafast statistical sampling with analog Ising machines by injecting noise. With an opto-electronic Ising machine, we experimentally demonstrate that this can be used for accurate sampling of Boltzmann distributions and for unsupervised training of neural networks, with equal accuracy as software-based training. Through simulations, we find that Ising machines can perform statistical sampling orders-of-magnitudes faster than software-based methods. This enables the use of Ising machines beyond combinatorial optimization and makes them into efficient tools for machine learning and other applications.

arXiv:2201.00695공식 코드 · Papers with Code

An Efficient Combinatorial Optimization Model Using Learning-to-Rank Distillation

Recently, deep reinforcement learning (RL) has proven its feasibility in solving combinatorial optimization problems (COPs). The learning-to-rank techniques have been studied in the field of information retrieval. While several COPs can be formulated as the prioritization of input items, as is common in the information retrieval, it has not been fully explored how the learning-to-rank techniques can be incorporated into deep RL for COPs. In this paper, we present the learning-to-rank distillation-based COP framework, where a high-performance ranking policy obtained by RL for a COP can be distilled into a non-iterative, simple model, thereby achieving a low-latency COP solver. Specifically, we employ the approximated ranking distillation to render a score-based ranking model learnable via gradient descent. Furthermore, we use the efficient sequence sampling to improve the inference performance with a limited delay. With the framework, we demonstrate that a distilled model not only achieves comparable performance to its respective, high-performance RL, but also provides several times faster inferences. We evaluate the framework with several COPs such as priority-based task scheduling and multidimensional knapsack, demonstrating the benefits of the framework in terms of inference latency and performance.

arXiv:2201.00668

Neural combinatorial optimization beyond the TSP: Existing architectures under-represent graph structure

Recent years have witnessed the promise that reinforcement learning, coupled with Graph Neural Network (GNN) architectures, could learn to solve hard combinatorial optimization problems: given raw input data and an evaluator to guide the process, the idea is to automatically learn a policy able to return feasible and high-quality outputs. Recent work have shown promising results but the latter were mainly evaluated on the travelling salesman problem (TSP) and similar abstract variants such as Split Delivery Vehicle Routing Problem (SDVRP). In this paper, we analyze how and whether recent neural architectures can be applied to graph problems of practical importance. We thus set out to systematically "transfer" these architectures to the Power and Channel Allocation Problem (PCAP), which has practical relevance for, e.g., radio resource allocation in wireless networks. Our experimental results suggest that existing architectures (i) are still incapable of capturing graph structural features and (ii) are not suitable for problems where the actions on the graph change the graph attributes. On a positive note, we show that augmenting the structural representation of problems with Distance Encoding is a promising step towards the still-ambitious goal of learning multi-purpose autonomous solvers.

arXiv:2201.00402

A General Framework for Evaluating Robustness of Combinatorial Optimization Solvers on Graphs

Solving combinatorial optimization (CO) on graphs is among the fundamental tasks for upper-stream applications in data mining, machine learning and operations research. Despite the inherent NP-hard challenge for CO, heuristics, branch-and-bound, learning-based solvers are developed to tackle CO problems as accurately as possible given limited time budgets. However, a practical metric for the sensitivity of CO solvers remains largely unexplored. Existing theoretical metrics require the optimal solution which is infeasible, and the gradient-based adversarial attack metric from deep learning is not compatible with non-learning solvers that are usually non-differentiable. In this paper, we develop the first practically feasible robustness metric for general combinatorial optimization solvers. We develop a no worse optimal cost guarantee thus do not require optimal solutions, and we tackle the non-differentiable challenge by resorting to black-box adversarial attack methods. Extensive experiments are conducted on 14 unique combinations of solvers and CO problems, and we demonstrate that the performance of state-of-the-art solvers like Gurobi can degenerate by over 20% under the given time limit bound on the hard instances discovered by our robustness metric, raising concerns about the robustness of combinatorial optimization solvers.

arXiv:2112.12985

DeepGANTT: A Scalable Deep Learning Scheduler for Backscatter Networks

Novel backscatter communication techniques enable battery-free sensor tags to interoperate with unmodified standard IoT devices, extending a sensor network's capabilities in a scalable manner. Without requiring additional dedicated infrastructure, the battery-free tags harvest energy from the environment, while the IoT devices provide them with the unmodulated carrier they need to communicate. A schedule coordinates the provision of carriers for the communications of battery-free devices with IoT nodes. Optimal carrier scheduling is an NP-hard problem that limits the scalability of network deployments. Thus, existing solutions waste energy and other valuable resources by scheduling the carriers suboptimally. We present DeepGANTT, a deep learning scheduler that leverages graph neural networks to efficiently provide near-optimal carrier scheduling. We train our scheduler with relatively small optimal schedules obtained from a constraint optimization solver, achieving a performance within 3% of the optimal scheduler. Without the need to retrain, DeepGANTT generalizes to networks 6x larger in the number of nodes and 10x larger in the number of tags than those used for training, breaking the scalability limitations of the optimal scheduler and reducing carrier utilization by up to 50% compared to the state-of-the-art heuristic. Our scheduler efficiently reduces energy and spectrum utilization in backscatter networks.

arXiv:2112.12345

Revisiting Transformation Invariant Geometric Deep Learning: Are Initial Representations All You Need?

Geometric deep learning, i.e., designing neural networks to handle the ubiquitous geometric data such as point clouds and graphs, have achieved great successes in the last decade. One critical inductive bias is that the model can maintain invariance towards various transformations such as translation, rotation, and scaling. The existing graph neural network (GNN) approaches can only maintain permutation-invariance, failing to guarantee invariance with respect to other transformations. Besides GNNs, other works design sophisticated transformation-invariant layers, which are computationally expensive and difficult to be extended. To solve this problem, we revisit why the existing neural networks cannot maintain transformation invariance when handling geometric data. Our findings show that transformation-invariant and distance-preserving initial representations are sufficient to achieve transformation invariance rather than needing sophisticated neural layer designs. Motivated by these findings, we propose Transformation Invariant Neural Networks (TinvNN), a straightforward and general framework for geometric data. Specifically, we realize transformation-invariant and distance-preserving initial point representations by modifying multi-dimensional scaling before feeding the representations into neural networks. We prove that TinvNN can strictly guarantee transformation invariance, being general and flexible enough to be combined with the existing neural networks. Extensive experimental results on point cloud analysis and combinatorial optimization demonstrate the effectiveness and general applicability of our proposed method. Based on the experimental results, we advocate that TinvNN should be considered a new starting point and an essential baseline for further studies of transformation-invariant geometric deep learning.

arXiv:2112.12545공식 코드 · Papers with Code

A Deep Reinforcement Learning Approach for Solving the Traveling Salesman Problem with Drone

Reinforcement learning has recently shown promise in learning quality solutions in many combinatorial optimization problems. In particular, the attention-based encoder-decoder models show high effectiveness on various routing problems, including the Traveling Salesman Problem (TSP). Unfortunately, they perform poorly for the TSP with Drone (TSP-D), requiring routing a heterogeneous fleet of vehicles in coordination -- a truck and a drone. In TSP-D, the two vehicles are moving in tandem and may need to wait at a node for the other vehicle to join. State-less attention-based decoder fails to make such coordination between vehicles. We propose a hybrid model that uses an attention encoder and a Long Short-Term Memory (LSTM) network decoder, in which the decoder's hidden state can represent the sequence of actions made. We empirically demonstrate that such a hybrid model improves upon a purely attention-based model for both solution quality and computational efficiency. Our experiments on the min-max Capacitated Vehicle Routing Problem (mmCVRP) also confirm that the hybrid model is more suitable for the coordinated routing of multiple vehicles than the attention-based model. The proposed model demonstrates comparable results as the operations research baseline methods.

arXiv:2112.12251

ML4CO: Is GCNN All You Need? Graph Convolutional Neural Networks Produce Strong Baselines For Combinatorial Optimization Problems, If Tuned and Trained Properly, on Appropriate Data

The 2021 NeurIPS Machine Learning for Combinatorial Optimization (ML4CO) competition was designed with the goal of improving state-of-the-art combinatorial optimization solvers by replacing key heuristic components with machine learning models. The competition's main scientific question was the following: is machine learning a viable option for improving traditional combinatorial optimization solvers on specific problem distributions, when historical data is available? This was motivated by the fact that in many practical scenarios, the data changes only slightly between the repetitions of a combinatorial optimization problem, and this is an area where machine learning models are particularly powerful at. This paper summarizes the solution and lessons learned by the Huawei EI-OROAS team in the dual task of the competition. The submission of our team achieved the second place in the final ranking, with a very close distance to the first spot. In addition, our solution was ranked first consistently for several weekly leaderboard updates before the final evaluation. We provide insights gained from a large number of experiments, and argue that a simple Graph Convolutional Neural Network (GCNNs) can achieve state-of-the-art results if trained and tuned properly.

arXiv:2112.10377

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.

arXiv:2112.04187공식 코드 · Papers with Code

Pretrained Cost Model for Distributed Constraint Optimization Problems

Distributed Constraint Optimization Problems (DCOPs) are an important subclass of combinatorial optimization problems, where information and controls are distributed among multiple autonomous agents. Previously, Machine Learning (ML) has been largely applied to solve combinatorial optimization problems by learning effective heuristics. However, existing ML-based heuristic methods are often not generalizable to different search algorithms. Most importantly, these methods usually require full knowledge about the problems to be solved, which are not suitable for distributed settings where centralization is not realistic due to geographical limitations or privacy concerns. To address the generality issue, we propose a novel directed acyclic graph representation schema for DCOPs and leverage the Graph Attention Networks (GATs) to embed graph representations. Our model, GAT-PCM, is then pretrained with optimally labelled data in an offline manner, so as to construct effective heuristics to boost a broad range of DCOP algorithms where evaluating the quality of a partial assignment is critical, such as local search or backtracking search. Furthermore, to enable decentralized model inference, we propose a distributed embedding schema of GAT-PCM where each agent exchanges only embedded vectors, and show its soundness and complexity. Finally, we demonstrate the effectiveness of our model by combining it with a local search or a backtracking search algorithm. Extensive empirical evaluations indicate that the GAT-PCM-boosted algorithms significantly outperform the state-of-the-art methods in various benchmarks. The pretrained model is available at https://github.com/dyc941126/GAT-PCM.

arXiv:2112.03512

Constrained Resource Allocation Problems in Communications: An Information-assisted Approach

We consider a class of resource allocation problems given a set of unconditional constraints whose objective function satisfies Bellman's optimality principle. Such problems are ubiquitous in wireless communication, signal processing, and networking. These constrained combinatorial optimization problems are, in general, NP-Hard. This paper proposes two algorithms to solve this class of problems using a dynamic programming framework assisted by an information-theoretic measure. We demonstrate that the proposed algorithms ensure optimal solutions under carefully chosen conditions and use significantly reduced computational resources. We substantiate our claims by solving the power-constrained bit allocation problem in 5G massive Multiple-Input Multiple-Output receivers using the proposed approach.

arXiv:2112.03609공식 코드 · Papers with Code

Decision-Focused Learning: Through the Lens of Learning to Rank

In the last years decision-focused learning framework, also known as predict-and-optimize, have received increasing attention. In this setting, the predictions of a machine learning model are used as estimated cost coefficients in the objective function of a discrete combinatorial optimization problem for decision making. Decision-focused learning proposes to train the ML models, often neural network models, by directly optimizing the quality of decisions made by the optimization solvers. Based on a recent work that proposed a noise contrastive estimation loss over a subset of the solution space, we observe that decision-focused learning can more generally be seen as a learning-to-rank problem, where the goal is to learn an objective function that ranks the feasible points correctly. This observation is independent of the optimization method used and of the form of the objective function. We develop pointwise, pairwise and listwise ranking loss functions, which can be differentiated in closed form given a subset of solutions. We empirically investigate the quality of our generic methods compared to existing decision-focused learning approaches with competitive results. Furthermore, controlling the subset of solutions allows controlling the runtime considerably, with limited effect on regret.

arXiv:2112.03346

Multidimensional Assignment Problem for multipartite entity resolution

Multipartite entity resolution aims at integrating records from multiple datasets into one entity. We derive a mathematical formulation for a general class of record linkage problems in multipartite entity resolution across many datasets as a combinatorial optimization problem known as the multidimensional assignment problem. As a motivation for our approach, we illustrate the advantage of multipartite entity resolution over sequential bipartite matching. Because the optimization problem is NP-hard, we apply two heuristic procedures, a Greedy algorithm and very large scale neighborhood search, to solve the assignment problem and find the most likely matching of records from multiple datasets into a single entity. We evaluate and compare the performance of these algorithms and their modifications on synthetically generated data. We perform computational experiments to compare performance of recent heuristic, the very large-scale neighborhood search, with a Greedy algorithm, another heuristic for the MAP, as well as with two versions of genetic algorithm, a general metaheuristic. Importantly, we perform experiments to compare two alternative methods of re-starting the search for the former heuristic, specifically a random-sampling multi-start and a deterministic design-based multi-start. We find evidence that design-based multi-start can be more efficient as the size of databases grow large. In addition, we show that very large scale search, especially its multi-start version, outperforms simple Greedy heuristic. Hybridization of Greedy search with very large scale neighborhood search improves the performance. Using multi-start with as few as three additional runs of very large scale search offers some improvement in the performance of the very large scale search procedure. Last, we propose an approach to evaluating complexity of the very large-scale neighborhood search.

arXiv:2112.03105

Active Learning Meets Optimized Item Selection

Designing recommendation systems with limited or no available training data remains a challenge. To that end, a new combinatorial optimization problem is formulated to generate optimized item selection for experimentation with the goal to shorten the time for collecting randomized training data. We first present an overview of the optimized item selection problem and a multi-level optimization framework to solve it. The approach integrates techniques from discrete optimization, unsupervised clustering, and latent text embeddings. We then discuss how to incorporate optimized item selection with active learning as part of randomized exploration in an ongoing fashion.

arXiv:2112.02843

Learning-based Measurement Scheduling for Loosely-Coupled Cooperative Localization

In cooperative localization, communicating mobile agents use inter-agent relative measurements to improve their dead-reckoning-based global localization. Measurement scheduling enables an agent to decide which subset of available inter-agent relative measurements it should process when its computational resources are limited. Optimal measurement scheduling is an NP-hard combinatorial optimization problem. The so-called sequential greedy (SG) algorithm is a popular suboptimal polynomial-time solution for this problem. However, the merit function evaluation for the SG algorithms requires access to the state estimate vector and error covariance matrix of all the landmark agents (teammates that an agent can take measurements from). This paper proposes a measurement scheduling for CL that follows the SG approach but reduces the communication and computation cost by using a neural network-based surrogate model as a proxy for the SG algorithm's merit function. The significance of this model is that it is driven by local information and only a scalar metadata from the landmark agents. This solution addresses the time and memory complexity issues of running the SG algorithm in three ways: (a) reducing the inter-agent communication message size, (b) decreasing the complexity of function evaluations by using a simpler surrogate (proxy) function, (c) reducing the required memory size.Simulations demonstrate our results.

arXiv:2112.01088

Constrained Machine Learning: The Bagel Framework

Machine learning models are widely used for real-world applications, such as document analysis and vision. Constrained machine learning problems are problems where learned models have to both be accurate and respect constraints. For continuous convex constraints, many works have been proposed, but learning under combinatorial constraints is still a hard problem. The goal of this paper is to broaden the modeling capacity of constrained machine learning problems by incorporating existing work from combinatorial optimization. We propose first a general framework called BaGeL (Branch, Generate and Learn) which applies Branch and Bound to constrained learning problems where a learning problem is generated and trained at each node until only valid models are obtained. Because machine learning has specific requirements, we also propose an extended table constraint to split the space of hypotheses. We validate the approach on two examples: a linear regression under configuration constraints and a non-negative matrix factorization with prior knowledge for latent semantics analysis.

arXiv:2112.00333

Joint Cluster Head Selection and Trajectory Planning in UAV-Aided IoT Networks by Reinforcement Learning with Sequential Model

Employing unmanned aerial vehicles (UAVs) has attracted growing interests and emerged as the state-of-the-art technology for data collection in Internet-of-Things (IoT) networks. In this paper, with the objective of minimizing the total energy consumption of the UAV-IoT system, we formulate the problem of jointly designing the UAV's trajectory and selecting cluster heads in the IoT network as a constrained combinatorial optimization problem which is classified as NP-hard and challenging to solve. We propose a novel deep reinforcement learning (DRL) with a sequential model strategy that can effectively learn the policy represented by a sequence-to-sequence neural network for the UAV's trajectory design in an unsupervised manner. Through extensive simulations, the obtained results show that the proposed DRL method can find the UAV's trajectory that requires much less energy consumption when compared to other baseline algorithms and achieves close-to-optimal performance. In addition, simulation results show that the trained model by our proposed DRL algorithm has an excellent generalization ability to larger problem sizes without the need to retrain the model.

arXiv:2111.14431

Eliciting and Distinguishing Between Weak and Incomplete Preferences: Theory, Experiment and Computation

Recovering and distinguishing between the strict-preference, indifference and/or indecisiveness parts of a decision maker's preferences is a challenging task but also important for testing theory and conducting welfare analysis. This paper contributes towards this goal by reporting on data from a lab experiment on riskless choice that were analyzed with novel theory-guided computational methods. The experiment included both Forced- and Free-Choice treatments. Its primary novelty consisted of allowing all subjects to select multiple alternatives at each menu. Based on a non-parametric goodness-of-fit criterion that we introduce, which generalizes intuitively a widely used pre-existing method to environments of multi-valued choices, each subjects' decision data were tested against three structured general-choice models that feature maximization of stable but potentially weak and/or incomplete preferences. Nearly 60% of all subjects' are well-explained by one of these models, typically with a unique model-optimal preference relation per subject. Importantly, preferences usually (80%) had a non-trivial indifference part and, where applicable, a clearly distinct indecisiveness part. The achieved uncoupling of revealed indifference and indecisiveness is documented empirically for the first time.

arXiv:2111.13628

Nonequilibrium Monte Carlo for unfreezing variables in hard combinatorial optimization

Optimizing highly complex cost/energy functions over discrete variables is at the heart of many open problems across different scientific disciplines and industries. A major obstacle is the emergence of many-body effects among certain subsets of variables in hard instances leading to critical slowing down or collective freezing for known stochastic local search strategies. An exponential computational effort is generally required to unfreeze such variables and explore other unseen regions of the configuration space. Here, we introduce a quantum-inspired family of nonlocal Nonequilibrium Monte Carlo (NMC) algorithms by developing an adaptive gradient-free strategy that can efficiently learn key instance-wise geometrical features of the cost function. That information is employed on-the-fly to construct spatially inhomogeneous thermal fluctuations for collectively unfreezing variables at various length scales, circumventing costly exploration versus exploitation trade-offs. We apply our algorithm to two of the most challenging combinatorial optimization problems: random k-satisfiability (k-SAT) near the computational phase transitions and Quadratic Assignment Problems (QAP). We observe significant speedup and robustness over both specialized deterministic solvers and generic stochastic solvers. In particular, for 90% of random 4-SAT instances we find solutions that are inaccessible for the best specialized deterministic algorithm known as Survey Propagation (SP) with an order of magnitude improvement in the quality of solutions for the hardest 10% instances. We also demonstrate two orders of magnitude improvement in time-to-solution over the state-of-the-art generic stochastic solver known as Adaptive Parallel Tempering (APT).

arXiv:2111.11858

Asteroid Flyby Cycler Trajectory Design Using Deep Neural Networks

Asteroid exploration has been attracting more attention in recent years. Nevertheless, we have just visited tens of asteroids while we have discovered more than one million bodies. As our current observation and knowledge should be biased, it is essential to explore multiple asteroids directly to better understand the remains of planetary building materials. One of the mission design solutions is utilizing asteroid flyby cycler trajectories with multiple Earth gravity assists. An asteroid flyby cycler trajectory design problem is a subclass of global trajectory optimization problems with multiple flybys, involving a trajectory optimization problem for a given flyby sequence and a combinatorial optimization problem to decide the sequence of the flybys. As the number of flyby bodies grows, the computation time of this optimization problem expands maliciously. This paper presents a new method to design asteroid flyby cycler trajectories utilizing a surrogate model constructed by deep neural networks approximating trajectory optimization results. Since one of the bottlenecks of machine learning approaches is the computation time to generate massive trajectory databases, we propose an efficient database generation strategy by introducing pseudo-asteroids satisfying the Karush-Kuhn-Tucker conditions. The numerical result applied to JAXA's DESTINY+ mission shows that the proposed method is practically applicable to space mission design and can significantly reduce the computational time for searching asteroid flyby sequences.