Stateful multicast protocols manage multicast group memberships by maintaining state information about active groups and their members. They have seen limited adoption in the modern internet due to lack of scalability, simplicity, and flexibility. Although stateless multicast protocols, like BIER, eliminate extensive state management, they still face complex tree computation and limited scalability for concurrent requests. In this paper, we propose Hawkeye, a stateless multicast mechanism with deep reinforcement learning (DRL) for real-time responses to dynamic multicast requests with near-optimal multicast TE performance. This mechanism is suited for Software-Defined Networking (SDN) environment where the controller has a global view of the network and supports flexible configuration of network resources for traffic engineering. For real-time responses to multicast requests, we leverage DRL enhanced by a temporal convolutional network (TCN) to model the sequential feature of dynamic group membership, and thus are able to build multicast trees proactively for upcoming requests. We develop a novel source aggregation mechanism to facilitate the convergence of the DRL agent under high volume of multicast requests. Moreover, to improve the practicality and robustness of Hawkeye, we design incremental deployment and single failure handling mechanisms, which take advantages of source aggregation and fit well with multicast routing. Evaluation with real-world topologies and multicast requests demonstrates that Hawkeye responds effectively to dynamic multicast requests. Itoffers rapid routing decisions, e.g., making routing decisions in under 5ms on a tested topology, and reduces path latency variation by up to 89.5%, with less than a 10% increase in bandwidth consumption compared to the offline theoretical minimum.

Complete search algorithms are important methods for solving Distributed Constraint Optimization Problems (DCOPs), which generally utilize bounds to prune the search space. However, obtaining high-quality lower bounds is quite expensive since it requires each agent to collect more information aside from its local knowledge, which would cause tremendous traffic overheads. Instead of bothering for bounds, we propose a Bound-Independent Pruning (BIP) technique for existing tree-based complete search algorithms, which can independently reduce the search space only by exploiting local knowledge. Specifically, BIP enables each agent to determine a subspace containing the optimal solution only from its local constraints along with running contexts, which can be further exploited by any search strategies. Furthermore, we present an acceptability testing mechanism to tailor existing tree-based complete search algorithms to search the remaining space returned by BIP when they hold inconsistent contexts. Finally, we prove the correctness of our technique and the experimental results show that BIP can significantly speed up state-of-the-art tree-based complete search algorithms on various standard benchmarks.

Search and inference are two main strategies for optimally solving Distributed Constraint Optimization Problems (DCOPs). Recently, several algorithms were proposed to combine their advantages. Unfortunately, such algorithms only use an approximated inference as a one-shot preprocessing phase to construct the initial lower bounds which lead to inefficient pruning under the limited memory budget. On the other hand, iterative inference algorithms (e.g., MB-DPOP) perform a context-based complete inference for all possible contexts but suffer from tremendous traffic overheads. In this paper, (i) hybridizing search with context-based inference, we propose a complete algorithm for DCOPs, named HS-CAI where the inference utilizes the contexts derived from the search process to establish tight lower bounds while the search uses such bounds for efficient pruning and thereby reduces contexts for the inference. Furthermore, (ii) we introduce a context evaluation mechanism to select the context patterns for the inference to further reduce the overheads incurred by iterative inferences. Finally, (iii) we prove the correctness of our algorithm and the experimental results demonstrate its superiority over the state-of-the-art.

Belief propagation approaches, such as Max-Sum and its variants, are important methods to solve large-scale Distributed Constraint Optimization Problems (DCOPs). However, for problems with n-ary constraints, these algorithms face a huge challenge since their computational complexity scales exponentially with the number of variables a function holds. In this paper, we present a generic and easy-touse method based on a branch-and-bound technique to solve the issue, called Function Decomposing and State Pruning (FDSP). We theoretically prove that FDSP can provide monotonically non-increasing upper bounds and speed up belief propagation based incomplete DCOP algorithms without an effect on solution quality. Also, our empirically evaluation indicates that FDSP can reduce 97% of the search space at least and effectively accelerate Max-Sum, compared with the state-of-the-art.

Asymmetric distributed constraint optimization problems (ADCOPs) are an emerging model for coordinating agents with personal preferences. However, the existing inference-based complete algorithms which use local eliminations cannot be applied to ADCOPs, as the parent agents are required to transfer their private functions to their children. Rather than disclosing private functions explicitly to facilitate local eliminations, we solve the problem by enforcing delayed eliminations and propose AsymDPOP, the first inference-based complete algorithm for ADCOPs. To solve the severe scalability problems incurred by delayed eliminations, we propose to reduce the memory consumption by propagating a set of smaller utility tables instead of a joint utility table, and to reduce the computation efforts by sequential optimizations instead of joint optimizations. The empirical evaluation indicates that AsymDPOP significantly outperforms the state-of-the-art, as well as the vanilla DPOP with PEAV formulation.

Because of affected by weather conditions, camera pose and range, etc. objects are usually small, blurry, occluded and diverse pose in the images, which are gathered from outdoor surveillance cameras or access control system. It is challenging and important to detect faces precisely for face recognition system in the field of public security. In this paper, we design a context modeling network named Feature Hierarchy Encoder-Decoder Network for face detection (FHEDN), which can detect small, blurry and occluded faces hierarchy by hierarchy from the end to the beginning in a single stage. The proposed network consists of encoder and decoder subnetworks. The encoder subnetwork constructs a multi-scale feature hierarchy pyramid through VGG-16 as backbone network. The decoder subnetwork models context semantic information around face and fuses it into the feature hierarchy for face detection. In addition, we analyze the influence of distribution of training set, scale of feature hierarchy and receipt field size on the detection performance in implement stage. The experiments demonstrate that our network achieves the promising performance on AFW, PASCAL FACE, WIDER FACE and FDDB benchmarks.

Construction of neural network ensembles (NNE) with sparse data requires comprehensive performance measure, multi-stage validation and usually a large member size. This paper presents a hybrid method which takes a selective optimization approach and is characterized with several novel features. First, candidate ensembles are widely explored using a multi-objective genetic algorithm. Secondly, the best local ensembles registered with each distinct objective weighting are determined based on the multi-stage validation results. Finally, a large global ensemble is formed by combining several local ensembles and virtually evaluated in the voids of possible parameter space. The demonstration of the proposed method is presented in a case study in which sparse data from FEA simulations are used to construct NNE for expandable pipe design, a novel application in oil and gas industry.

This paper discusses a hybrid method for construction of neural network ensembles (NNE) in generating synthetic well logs that is often driven by the needs of simulating unobtainable actual logs, reducing the operational cost, reconstruction of missing and / or bad log data, and minimizing the hazards associated with using radioactive sources. In this method, several computer-driven routines are developed to rank the candidate neural network inputs as a function of data partition, network complexity and initialization. Then a network pool is automatically formed having the selected candidate networks characterized with multi-set inputs and different hidden nodes. The ensemble optimization is performed using a multi-objective genetic algorithm by aggregating the ensemble validation error, complexity, and negative correlation into a single quantity of merit. The simulations applied to actual field examples demonstrate that using multi-set-input NNE is more robust than using single-set-input NNE with significantly reduced uncertainty and improved prediction accuracy on the new data for some applications.

This paper proposes a new framework for adapting regularization parameters in order to minimize validation error during the training of feedforward neural networks. A second derivative of validation error based regularization algorithm (SDVR) is derived using the Gauss-Newton approximation to the Hessian. The basic algorithm, which uses incremental updating, allows the regularization parameter /spl alpha/ to be recalculated in each training epoch. Two variations of the algorithm, called convergent updating and conditional updating, enable /spl alpha/ to be updated over a variable interval according to the specified control criteria. Simulations on a noise-corrupted parabolic function with two-inputs and a single output are investigated. The results demonstrate that the SDVR framework is very promising for adaptive regularization and can be cost effectively applied to a variety of different problems.