arXiv subjects

Ke Tang

Publications and source records attributed to Ke Tang.

At least 127 records · Page 7Linked to original sources

arXiv2021

A New Knowledge Gradient-based Method for Constrained Bayesian Optimization

Black-box problems are common in real life like structural design, drug experiments, and machine learning. When optimizing black-box systems, decision-makers always consider multiple performances and give the final decision by comprehensive evaluations. Motivated by such practical needs, we focus on constrained black-box problems where the objective and constraints lack known special structure, and evaluations are expensive and even with noise. We develop a novel constrained Bayesian optimization approach based on the knowledge gradient method ($c-\rm{KG}$). A new acquisition function is proposed to determine the next batch of samples considering optimality and feasibility. An unbiased estimator of the gradient of the new acquisition function is derived to implement the $c-\rm{KG}$ approach.

cs.LG↗

arXiv2021

Magnetization switching induced by spin-orbit torque from Co2MnGa magnetic Weyl semimetal thin films

This study reports the magnetization switching induced by spin-orbit torque (SOT) from the spin current generated in Co2MnGa magnetic Weyl semimetal (WSM) thin films. We deposited epitaxial Co2MnGa thin films with highly B2-ordered structure on MgO(001) substrates. The SOT was characterized by harmonic Hall measurements in a Co2MnGa/Ti/CoFeB heterostructure and a relatively large spin Hall efficiency of -7.8% was obtained.The SOT-induced magnetization switching of the perpendicularly magnetized CoFeB layer was further demonstrated using the structure. The symmetry of second harmonic signals, thickness dependence of spin Hall efficiency, and shift of anomalous Hall loops under applied currents were also investigated. This study not only contributes to the understanding of the mechanisms of spin-current generation from magnetic-WSM-based heterostructures, but also paves a way for the applications of magnetic WSMs in spintronic devices.

cond-mat.mtrl-sci↗

arXiv2020

Interpreting Deep Learning Model Using Rule-based Method

Deep learning models are favored in many research and industry areas and have reached the accuracy of approximating or even surpassing human level. However they've long been considered by researchers as black-box models for their complicated nonlinear property. In this paper, we propose a multi-level decision framework to provide comprehensive interpretation for the deep neural network model. In this multi-level decision framework, by fitting decision trees for each neuron and aggregate them together, a multi-level decision structure (MLD) is constructed at first, which can approximate the performance of the target neural network model with high efficiency and high fidelity. In terms of local explanation for sample, two algorithms are proposed based on MLD structure: forward decision generation algorithm for providing sample decisions, and backward rule induction algorithm for extracting sample rule-mapping recursively. For global explanation, frequency-based and out-of-bag based methods are proposed to extract important features in the neural network decision. Furthermore, experiments on the MNIST and National Free Pre-Pregnancy Check-up (NFPC) dataset are carried out to demonstrate the effectiveness and interpretability of MLD framework. In the evaluation process, both functionally-grounded and human-grounded methods are used to ensure credibility.

cs.LG↗

arXiv2020

Evolutionary Reinforcement Learning via Cooperative Coevolutionary Negatively Correlated Search

Evolutionary algorithms (EAs) have been successfully applied to optimize the policies for Reinforcement Learning (RL) tasks due to their exploration ability. The recently proposed Negatively Correlated Search (NCS) provides a distinct parallel exploration search behavior and is expected to facilitate RL more effectively. Considering that the commonly adopted neural policies usually involves millions of parameters to be optimized, the direct application of NCS to RL may face a great challenge of the large-scale search space. To address this issue, this paper presents an NCS-friendly Cooperative Coevolution (CC) framework to scale-up NCS while largely preserving its parallel exploration search behavior. The issue of traditional CC that can deteriorate NCS is also discussed. Empirical studies on 10 popular Atari games show that the proposed method can significantly outperform three state-of-the-art deep RL methods with 50% less computational time by effectively exploring a 1.7 million-dimensional search space.

cs.NE↗

arXiv2020

Parallel Exploration via Negatively Correlated Search

Effective exploration is a key to successful search. The recently proposed Negatively Correlated Search (NCS) tries to achieve this by parallel exploration, where a set of search processes are driven to be negatively correlated so that different promising areas of the search space can be visited simultaneously. Various applications have verified the advantages of such novel search behaviors. Nevertheless, the mathematical understandings are still lacking as the previous NCS was mostly devised by intuition. In this paper, a more principled NCS is presented, explaining that the parallel exploration is equivalent to the explicit maximization of both the population diversity and the population solution qualities, and can be optimally obtained by partially gradient descending both models with respect to each search process. For empirical assessments, the reinforcement learning tasks that largely demand exploration ability is considered. The new NCS is applied to the popular reinforcement learning problems, i.e., playing Atari games, to directly train a deep convolution network with 1.7 million connection weights in the environments with uncertain and delayed rewards. Empirical results show that the significant advantages of NCS over the compared state-of-the-art methods can be highly owed to the effective parallel exploration ability.

cs.NE↗

arXiv2019

Stochastic Gradient Descent for Nonconvex Learning without Bounded Gradient Assumptions

Stochastic gradient descent (SGD) is a popular and efficient method with wide applications in training deep neural nets and other nonconvex models. While the behavior of SGD is well understood in the convex learning setting, the existing theoretical results for SGD applied to nonconvex objective functions are far from mature. For example, existing results require to impose a nontrivial assumption on the uniform boundedness of gradients for all iterates encountered in the learning process, which is hard to verify in practical implementations. In this paper, we establish a rigorous theoretical foundation for SGD in nonconvex learning by showing that this boundedness assumption can be removed without affecting convergence rates. In particular, we establish sufficient conditions for almost sure convergence as well as optimal convergence rates for SGD applied to both general nonconvex objective functions and gradient-dominated objective functions. A linear convergence is further derived in the case with zero variances.

cs.LG↗

arXiv2019

Competitive Coevolution as an Adversarial Approach to Dynamic Optimization

Dynamic optimization, for which the objective functions change over time, has attracted intensive investigations due to the inherent uncertainty associated with many real-world problems. For its robustness with respect to noise, Evolutionary Algorithms (EAs) have been expected to have great potential for dynamic optimization. On the other hand, EAs are also criticized for its high computational complexity, which appears to be contradictory to the core requirement of real-world dynamic optimization, i.e., fast adaptation (typically in terms of wall-clock time) to the environmental change. So far, whether EAs would indeed lead to a truly effective approach for real-world dynamic optimization remain unclear. In this paper, a new framework of employing EAs in the context of dynamic optimization is explored. We suggest that, instead of online evolving (searching) solutions for the ever-changing objective function, EAs are more suitable for acquiring an archive of solutions in an offline way, which could be adopted to construct a system to provide high-quality solutions efficiently in a dynamic environment. To be specific, we first re-formulate dynamic optimization problems as static set-oriented optimization problems. Then, a particular type of EAs, namely competitive coevolution, is employed to search for the archive of solutions in an adversarial way. The general framework is instantiated for continuous dynamic constrained optimization problems, and the empirical results showed the potential of the proposed framework.

cs.NE↗

arXiv2019

On Performance Estimation in Automatic Algorithm Configuration

Over the last decade, research on automated parameter tuning, often referred to as automatic algorithm configuration (AAC), has made significant progress. Although the usefulness of such tools has been widely recognized in real world applications, the theoretical foundations of AAC are still very weak. This paper addresses this gap by studying the performance estimation problem in AAC. More specifically, this paper first proves the universal best performance estimator in a practical setting, and then establishes theoretical bounds on the estimation error, i.e., the difference between the training performance and the true performance for a parameter configuration, considering finite and infinite configuration spaces respectively. These findings were verified in extensive experiments conducted on four algorithm configuration scenarios involving different problem domains. Moreover, insights for enhancing existing AAC methods are also identified.

cs.LG↗

arXiv2019

DynWalks: Global Topology and Recent Changes Awareness Dynamic Network Embedding

Learning topological representation of a network in dynamic environments has recently attracted considerable attention due to the time-evolving nature of many real-world networks i.e. nodes/links might be added/removed as time goes on. Dynamic network embedding aims to learn low dimensional embeddings for unseen and seen nodes by using any currently available snapshots of a dynamic network. For seen nodes, the existing methods either treat them equally important or focus on the $k$ most affected nodes at each time step. However, the former solution is time-consuming, and the later solution that relies on incoming changes may lose the global topology---an important feature for downstream tasks. To address these challenges, we propose a dynamic network embedding method called DynWalks, which includes two key components: 1) An online network embedding framework that can dynamically and efficiently learn embeddings based on the selected nodes; 2) A novel online node selecting scheme that offers the flexible choices to balance global topology and recent changes, as well as to fulfill the real-time constraint if needed. The empirical studies on six real-world dynamic networks under three different slicing ways show that DynWalks significantly outperforms the state-of-the-art methods in graph reconstruction tasks, and obtains comparable results in link prediction tasks. Furthermore, the wall-clock time and complexity analysis demonstrate its excellent time and space efficiency. The source code of DynWalks is available at https://github.com/houchengbin/DynWalks

cs.SI↗

arXiv2019

AlphaStock: A Buying-Winners-and-Selling-Losers Investment Strategy using Interpretable Deep Reinforcement Attention Networks

Recent years have witnessed the successful marriage of finance innovations and AI techniques in various finance applications including quantitative trading (QT). Despite great research efforts devoted to leveraging deep learning (DL) methods for building better QT strategies, existing studies still face serious challenges especially from the side of finance, such as the balance of risk and return, the resistance to extreme loss, and the interpretability of strategies, which limit the application of DL-based strategies in real-life financial markets. In this work, we propose AlphaStock, a novel reinforcement learning (RL) based investment strategy enhanced by interpretable deep attention networks, to address the above challenges. Our main contributions are summarized as follows: i) We integrate deep attention networks with a Sharpe ratio-oriented reinforcement learning framework to achieve a risk-return balanced investment strategy; ii) We suggest modeling interrelationships among assets to avoid selection bias and develop a cross-asset attention mechanism; iii) To our best knowledge, this work is among the first to offer an interpretable investment strategy using deep reinforcement learning models. The experiments on long-periodic U.S. and Chinese markets demonstrate the effectiveness and robustness of AlphaStock over diverse market states. It turns out that AlphaStock tends to select the stocks as winners with high long-term growth, low volatility, high intrinsic value, and being undervalued recently.

q-fin.TR↗

arXiv2019

Attributed Network Embedding for Incomplete Attributed Networks

Attributed networks are ubiquitous since a network often comes with auxiliary attribute information e.g. a social network with user profiles. Attributed Network Embedding (ANE) has recently attracted considerable attention, which aims to learn unified low dimensional node embeddings while preserving both structural and attribute information. The resulting node embeddings can then facilitate various network downstream tasks e.g. link prediction. Although there are several ANE methods, most of them cannot deal with incomplete attributed networks with missing links and/or missing node attributes, which often occur in real-world scenarios. To address this issue, we propose a robust ANE method, the general idea of which is to reconstruct a unified denser network by fusing two sources of information for information enhancement, and then employ a random walks based network embedding method for learning node embeddings. The experiments of link prediction, node classification, visualization, and parameter sensitivity analysis on six real-world datasets validate the effectiveness of our method to incomplete attributed networks.

cs.SI↗

arXiv2019

Decision Making with Machine Learning and ROC Curves

The Receiver Operating Characteristic (ROC) curve is a representation of the statistical information discovered in binary classification problems and is a key concept in machine learning and data science. This paper studies the statistical properties of ROC curves and its implication on model selection. We analyze the implications of different models of incentive heterogeneity and information asymmetry on the relation between human decisions and the ROC curves. Our theoretical discussion is illustrated in the context of a large data set of pregnancy outcomes and doctor diagnosis from the Pre-Pregnancy Checkups of reproductive age couples in Henan Province provided by the Chinese Ministry of Health.

stat.ME↗

arXiv2019

Maximizing Monotone DR-submodular Continuous Functions by Derivative-free Optimization

In this paper, we study the problem of monotone (weakly) DR-submodular continuous maximization. While previous methods require the gradient information of the objective function, we propose a derivative-free algorithm LDGM for the first time. We define $β$ and $α$ to characterize how close a function is to continuous DR-submodulr and submodular, respectively. Under a convex polytope constraint, we prove that LDGM can achieve a $(1-e^{-β}-ε)$-approximation guarantee after $O(1/ε)$ iterations, which is the same as the best previous gradient-based algorithm. Moreover, in some special cases, a variant of LDGM can achieve a $((α/2)(1-e^{-α})-ε)$-approximation guarantee for (weakly) submodular functions. We also compare LDGM with the gradient-based algorithm Frank-Wolfe under noise, and show that LDGM can be more robust. Empirical results on budget allocation verify the effectiveness of LDGM.

cs.LG↗

arXiv2018

A Parallel Divide-and-Conquer based Evolutionary Algorithm for Large-scale Optimization

Large-scale optimization problems that involve thousands of decision variables have extensively arisen from various industrial areas. As a powerful optimization tool for many real-world applications, evolutionary algorithms (EAs) fail to solve the emerging large-scale problems both effectively and efficiently. In this paper, we propose a novel Divide-and-Conquer (DC) based EA that can not only produce high-quality solution by solving sub-problems separately, but also highly utilizes the power of parallel computing by solving the sub-problems simultaneously. Existing DC-based EAs that were deemed to enjoy the same advantages of the proposed algorithm, are shown to be practically incompatible with the parallel computing scheme, unless some trade-offs are made by compromising the solution quality.

cs.NE↗

arXiv2018

Experience-based Optimization: A Coevolutionary Approach

This paper studies improving solvers based on their past solving experiences, and focuses on improving solvers by offline training. Specifically, the key issues of offline training methods are discussed, and research belonging to this category but from different areas are reviewed in a unified framework. Existing training methods generally adopt a two-stage strategy in which selecting the training instances and training instances are treated in two independent phases. This paper proposes a new training method, dubbed LiangYi, which addresses these two issues simultaneously. LiangYi includes a training module for a population-based solver and an instance sampling module for updating the training instances. The idea behind LiangYi is to promote the population-based solver by training it (with the training module) to improve its performance on those instances (discovered by the sampling module) on which it performs badly, while keeping the good performances obtained by it on previous instances. An instantiation of LiangYi on the Travelling Salesman Problem is also proposed. Empirical results on a huge testing set containing 10000 instances showed LiangYi could train solvers that perform significantly better than the solvers trained by other state-of-the-art training method. Moreover, empirical investigation of the behaviours of LiangYi confirmed it was able to continuously improve the solver through training.

cs.NE↗

arXiv2018

Automatic Construction of Parallel Portfolios via Explicit Instance Grouping

Simultaneously utilizing several complementary solvers is a simple yet effective strategy for solving computationally hard problems. However, manually building such solver portfolios typically requires considerable domain knowledge and plenty of human effort. As an alternative, automatic construction of parallel portfolios (ACPP) aims at automatically building effective parallel portfolios based on a given problem instance set and a given rich design space. One promising way to solve the ACPP problem is to explicitly group the instances into different subsets and promote a component solver to handle each of them.This paper investigates solving ACPP from this perspective, and especially studies how to obtain a good instance grouping.The experimental results showed that the parallel portfolios constructed by the proposed method could achieve consistently superior performances to the ones constructed by the state-of-the-art ACPP methods,and could even rival sophisticated hand-designed parallel solvers.

cs.AI↗

arXiv2017

Preselection via Classification: A Case Study on Evolutionary Multiobjective Optimization

In evolutionary algorithms, a preselection operator aims to select the promising offspring solutions from a candidate offspring set. It is usually based on the estimated or real objective values of the candidate offspring solutions. In a sense, the preselection can be treated as a classification procedure, which classifies the candidate offspring solutions into promising ones and unpromising ones. Following this idea, we propose a classification based preselection (CPS) strategy for evolutionary multiobjective optimization. When applying classification based preselection, an evolutionary algorithm maintains two external populations (training data set) that consist of some selected good and bad solutions found so far; then it trains a classifier based on the training data set in each generation. Finally it uses the classifier to filter the unpromising candidate offspring solutions and choose a promising one from the generated candidate offspring set for each parent solution. In such cases, it is not necessary to estimate or evaluate the objective values of the candidate offspring solutions. The classification based preselection is applied to three state-of-the-art multiobjective evolutionary algorithms (MOEAs) and is empirically studied on two sets of test instances. The experimental results suggest that classification based preselection can successfully improve the performance of these MOEAs.

cs.NE↗

arXiv2017

Evolutionary Multitasking for Single-objective Continuous Optimization: Benchmark Problems, Performance Metric, and Baseline Results

In this report, we suggest nine test problems for multi-task single-objective optimization (MTSOO), each of which consists of two single-objective optimization tasks that need to be solved simultaneously. The relationship between tasks varies between different test problems, which would be helpful to have a comprehensive evaluation of the MFO algorithms. It is expected that the proposed test problems will germinate progress the field of the MTSOO research.

cs.NE↗