Discrete optimization

About: Discrete optimization is a research topic. Over the lifetime, 4598 publications have been published within this topic receiving 158297 citations. The topic is also known as: discrete optimisation.

Difficult features of combinatorial optimization problems and the tunable w-model benchmark problem for simulating them

Abstract: The first event of the Black-Box Discrete Optimization Benchmarking (BB-DOB) workshop series aims to establish a set of example problems for benchmarking black-box optimization algorithms for discrete or combinatorial domains In this paper, we 1) discuss important features that should be embodied by these benchmark functions and 2) present the W-Model problem which exhibits them The W-Model follows a layered approach, where each layer can either be omitted or introduce a different characteristic feature such as neutrality via redundancy, ruggedness and deceptiveness, epistasis, and multi-objectivity, in a tunable way The model problem is defined over bit string representations, which allows for extracting some of its layers and stacking them on top of existing problems that use this representation, such as OneMax, the Maximum Satisfiability or the Set Covering tasks, and the NK landscape The ruggedness and deceptiveness layer can be stacked on top of any problem with integer-valued objectives We put the W-Model into the context of related model problems targeting ruggedness, neutrality, and epistasis We then present the results of a series of experiments to further substantiate the utility of the W-Model and to give an idea about suitable configurations of it that could be included in the BB-DOB benchmark suite

A technique of global optimization of microprograms

Abstract: This paper describes a technique of global optimization of microprograms including loops and recursive subroutines. This technique can be applied to a wide variety of microprogrammable machines. The principle of global optimization, four basic types of global optimization, and extended types of global optimization are discussed and the optimization algorithm is shown. Its effectiveness is evaluated and confirmed by applying it to an existing microprogrammable computer composed of LSI processor modules.

Information-Maximization Clustering based on Squared-Loss Mutual Information

Abstract: Information-maximization clustering learns a probabilistic classifier in an unsupervised manner so that mutual information between feature vectors and cluster assignments is maximized. A notable advantage of this approach is that it only involves continuous optimization of model parameters, which is substantially easier to solve than discrete optimization of cluster assignments. However, existing methods still involve non-convex optimization problems, and therefore finding a good local optimal solution is not straightforward in practice. In this paper, we propose an alternative information-maximization clustering method based on a squared-loss variant of mutual information. This novel approach gives a clustering solution analytically in a computationally efficient way via kernel eigenvalue decomposition. Furthermore, we provide a practical model selection procedure that allows us to objectively optimize tuning parameters included in the kernel function. Through experiments, we demonstrate the usefulness of the proposed approach.

Securing the Deep Fraud Detector in Large-Scale E-Commerce Platform via Adversarial Machine Learning Approach

Abstract: Fraud transactions are one of the major threats faced by online e-commerce platforms. Recently, deep learning based classifiers have been deployed to detect fraud transactions. Inspired by findings on adversarial examples, this paper is the first to analyze the vulnerability of deep fraud detector to slight perturbations on input transactions, which is very challenging since the sparsity and discretization of transaction data result in a non-convex discrete optimization. Inspired by the iterative Fast Gradient Sign Method (FGSM) for the L8 attack, we first propose the Iterative Fast Coordinate Method (IFCM) for discrete L1 and L2 attacks which is efficient to generate large amounts of instances with satisfactory effectiveness. We then provide two novel attack algorithms to solve the discrete optimization. The first one is the Augmented Iterative Search (AIS) algorithm, which repeatedly searches for effective “simple” perturbation. The second one is called the Rounded Relaxation with Reparameterization (R3), which rounds the solution obtained by solving a relaxed and unconstrained optimization problem with reparameterization tricks. Finally, we conduct extensive experimental evaluation on the deployed fraud detector in TaoBao, one of the largest e-commerce platforms in the world, with millions of real-world transactions. Results show that (i) The deployed detector is highly vulnerable to attacks as the average precision is decreased from nearly 90% to as low as 20% with little perturbations; (ii) Our proposed attacks significantly outperform the adaptions of the state-of-the-art attacks. (iii) The model trained with an adversarial training process is significantly robust against attacks and performs well on the unperturbed data.