arXiv subjects

Zhe Xu

Publications and source records attributed to Zhe Xu.

At least 181 records · Page 10Linked to original sources

arXiv2021

Byzantine-Resilient Distributed Hypothesis Testing With Time-Varying Network Topology

We study the problem of distributed hypothesis testing over a network of mobile agents with limited communication and sensing ranges to infer the true hypothesis collaboratively. In particular, we consider a scenario where there is an unknown subset of compromised agents that may deliberately share altered information to undermine the team objective. We propose two distributed algorithms where each agent maintains and updates two sets of beliefs (i.e., probability distributions over the hypotheses), namely local and actual beliefs (LB and AB respectively for brevity). In both algorithms, at every time step, each agent shares its AB with other agents within its communication range and makes a local observation to update its LB. Then both algorithms can use the shared information to update ABs under certain conditions. One requires receiving a certain number of shared ABs at each time instant; the other accumulates shared ABs over time and updates after the number of shared ABs exceeds a prescribed threshold. Otherwise, both algorithms rely on the agent's current LB and AB to update the new AB. We prove under mild assumptions that the AB for every non-compromised agent converges almost surely to the true hypothesis, without requiring connectivity in the underlying time-varying network topology. Using a simulation of a team of unmanned aerial vehicles aiming to classify adversarial agents among themselves, we illustrate and compare the proposed algorithms. Finally, we show experimentally that the second algorithm consistently outperforms the first algorithm in terms of the speed of convergence.

eess.SY↗

arXiv2021

Active Finite Reward Automaton Inference and Reinforcement Learning Using Queries and Counterexamples

Despite the fact that deep reinforcement learning (RL) has surpassed human-level performances in various tasks, it still has several fundamental challenges. First, most RL methods require intensive data from the exploration of the environment to achieve satisfactory performance. Second, the use of neural networks in RL renders it hard to interpret the internals of the system in a way that humans can understand. To address these two challenges, we propose a framework that enables an RL agent to reason over its exploration process and distill high-level knowledge for effectively guiding its future explorations. Specifically, we propose a novel RL algorithm that learns high-level knowledge in the form of a finite reward automaton by using the L* learning algorithm. We prove that in episodic RL, a finite reward automaton can express any non-Markovian bounded reward functions with finitely many reward values and approximate any non-Markovian bounded reward function (with infinitely many reward values) with arbitrary precision. We also provide a lower bound for the episode length such that the proposed RL approach almost surely converges to an optimal policy in the limit. We test this approach on two RL environments with non-Markovian reward functions, choosing a variety of tasks with increasing complexity for each environment. We compare our algorithm with the state-of-the-art RL algorithms for non-Markovian reward functions, such as Joint Inference of Reward machines and Policies for RL (JIRP), Learning Reward Machine (LRM), and Proximal Policy Optimization (PPO2). Our results show that our algorithm converges to an optimal policy faster than other baseline methods.

cs.LG↗

arXiv2021

Probabilistic Control of Heterogeneous Swarms Subject to Graph Temporal Logic Specifications: A Decentralized and Scalable Approach

We develop a probabilistic control algorithm, $\texttt{GTLProCo}$, for swarms of agents with heterogeneous dynamics and objectives, subject to high-level task specifications. The resulting algorithm not only achieves decentralized control of the swarm but also significantly improves scalability over state-of-the-art existing algorithms. Specifically, we study a setting in which the agents move along the nodes of a graph, and the high-level task specifications for the swarm are expressed in a recently-proposed language called graph temporal logic (GTL). By constraining the distribution of the swarm over the nodes of the graph, GTL can specify a wide range of properties, including safety, progress, and response. $\texttt{GTLProCo}$, agnostic to the number of agents comprising the swarm, controls the density distribution of the swarm in a decentralized and probabilistic manner. To this end, it synthesizes a time-varying Markov chain modeling the time evolution of the density distribution under the GTL constraints. We first identify a subset of GTL, namely reach-avoid specifications, for which we can reduce the synthesis of such a Markov chain to either linear or semi-definite programs. Then, in the general case, we formulate the synthesis of the Markov chain as a mixed-integer nonlinear program (MINLP). We exploit the structure of the problem to provide an efficient sequential mixed-integer linear programming scheme with trust regions to solve the MINLP. We empirically demonstrate that our sequential scheme is at least three orders of magnitude faster than off-the-shelf MINLP solvers and illustrate the effectiveness of $\texttt{GTLProCo}$ in several swarm scenarios.

eess.SY↗

arXiv2021

Learning Linear Temporal Properties from Noisy Data: A MaxSAT Approach

We address the problem of inferring descriptions of system behavior using Linear Temporal Logic (LTL) from a finite set of positive and negative examples. Most of the existing approaches for solving such a task rely on predefined templates for guiding the structure of the inferred formula. The approaches that can infer arbitrary LTL formulas, on the other hand, are not robust to noise in the data. To alleviate such limitations, we devise two algorithms for inferring concise LTL formulas even in the presence of noise. Our first algorithm infers minimal LTL formulas by reducing the inference problem to a problem in maximum satisfiability and then using off-the-shelf MaxSAT solvers to find a solution. To the best of our knowledge, we are the first to incorporate the usage of MaxSAT solvers for inferring formulas in LTL. Our second learning algorithm relies on the first algorithm to derive a decision tree over LTL formulas based on a decision tree learning algorithm. We have implemented both our algorithms and verified that our algorithms are efficient in extracting concise LTL descriptions even in the presence of noise.

cs.LG↗

arXiv2021

Privacy-Utility Trade-Offs Against Limited Adversaries

We study privacy-utility trade-offs where users share privacy-correlated useful information with a service provider to obtain some utility. The service provider is adversarial in the sense that it can infer the users' private information based on the shared useful information. To minimize the privacy leakage while maintaining a desired level of utility, the users carefully perturb the useful information via a probabilistic privacy mapping before sharing it. We focus on the setting in which the adversary attempting an inference attack on the users' privacy has potentially biased information about the statistical correlation between the private and useful variables. This information asymmetry between the users and the limited adversary leads to better privacy guarantees than the case of the omniscient adversary under the same utility requirement. We first identify assumptions on the adversary's information so that the inference costs are well-defined and finite. Then, we characterize the impact of the information asymmetry and show that it increases the inference costs for the adversary. We further formulate the design of the privacy mapping against a limited adversary using a difference of convex functions program and solve it via the concave-convex procedure. When the adversary's information is not precisely available, we adopt a Bayesian view and represent the adversary's information by a probability distribution. In this case, the expected cost for the adversary does not admit a closed-form expression, and we establish and maximize a lower bound of the expected cost. We provide a numerical example regarding a census data set to illustrate the theoretical results.

cs.IT↗

arXiv2021

A Deep Value-network Based Approach for Multi-Driver Order Dispatching

Recent works on ride-sharing order dispatching have highlighted the importance of taking into account both the spatial and temporal dynamics in the dispatching process for improving the transportation system efficiency. At the same time, deep reinforcement learning has advanced to the point where it achieves superhuman performance in a number of fields. In this work, we propose a deep reinforcement learning based solution for order dispatching and we conduct large scale online A/B tests on DiDi's ride-dispatching platform to show that the proposed method achieves significant improvement on both total driver income and user experience related metrics. In particular, we model the ride dispatching problem as a Semi Markov Decision Process to account for the temporal aspect of the dispatching actions. To improve the stability of the value iteration with nonlinear function approximators like neural networks, we propose Cerebellar Value Networks (CVNet) with a novel distributed state representation layer. We further derive a regularized policy evaluation scheme for CVNet that penalizes large Lipschitz constant of the value network for additional robustness against adversarial perturbation and noises. Finally, we adapt various transfer learning methods to CVNet for increased learning adaptability and efficiency across multiple cities. We conduct extensive offline simulations based on real dispatching data as well as online AB tests through the DiDi's platform. Results show that CVNet consistently outperforms other recently proposed dispatching methods. We finally show that the performance can be further improved through the efficient use of transfer learning.

cs.LG↗

arXiv2021

Noisy Labels are Treasure: Mean-Teacher-Assisted Confident Learning for Hepatic Vessel Segmentation

Manually segmenting the hepatic vessels from Computer Tomography (CT) is far more expertise-demanding and laborious than other structures due to the low-contrast and complex morphology of vessels, resulting in the extreme lack of high-quality labeled data. Without sufficient high-quality annotations, the usual data-driven learning-based approaches struggle with deficient training. On the other hand, directly introducing additional data with low-quality annotations may confuse the network, leading to undesirable performance degradation. To address this issue, we propose a novel mean-teacher-assisted confident learning framework to robustly exploit the noisy labeled data for the challenging hepatic vessel segmentation task. Specifically, with the adapted confident learning assisted by a third party, i.e., the weight-averaged teacher model, the noisy labels in the additional low-quality dataset can be transformed from "encumbrance" to "treasure" via progressive pixel-wise soft-correction, thus providing productive guidance. Extensive experiments using two public datasets demonstrate the superiority of the proposed framework as well as the effectiveness of each component.

eess.IV↗

arXiv2021

Distributed Policy Synthesis of Multi-Agent Systems With Graph Temporal Logic Specifications

We study the distributed synthesis of policies for multi-agent systems to perform \emph{spatial-temporal} tasks. We formalize the synthesis problem as a \emph{factored} Markov decision process subject to \emph{graph temporal logic} specifications. The transition function and task of each agent are functions of the agent itself and its neighboring agents. In this work, we develop another distributed synthesis method, which improves the scalability and runtime by two orders of magnitude compared to our prior work. The synthesis method decomposes the problem into a set of smaller problems, one for each agent by leveraging the structure in the model, and the specifications. We show that the running time of the method is linear in the number of agents. The size of the problem for each agent is exponential only in the number of neighboring agents, which is typically much smaller than the number of agents. We demonstrate the applicability of the method in case studies on disease control, urban security, and search and rescue. The numerical examples show that the method scales to hundreds of agents with hundreds of states per agent and can also handle significantly larger state spaces than our prior work.

cs.MA↗

arXiv2021

Uncertainty-Aware Signal Temporal Logic Inference

Temporal logic inference is the process of extracting formal descriptions of system behaviors from data in the form of temporal logic formulas. The existing temporal logic inference methods mostly neglect uncertainties in the data, which results in limited applicability of such methods in real-world deployments. In this paper, we first investigate the uncertainties associated with trajectories of a system and represent such uncertainties in the form of interval trajectories. We then propose two uncertainty-aware signal temporal logic (STL) inference approaches to classify the undesired behaviors and desired behaviors of a system. Instead of classifying finitely many trajectories, we classify infinitely many trajectories within the interval trajectories. In the first approach, we incorporate robust semantics of STL formulas with respect to an interval trajectory to quantify the margin at which an STL formula is satisfied or violated by the interval trajectory. The second approach relies on the first learning algorithm and exploits the decision tree to infer STL formulas to classify behaviors of a given system. The proposed approaches also work for non-separable data by optimizing the worst-case robustness in inferring an STL formula. Finally, we evaluate the performance of the proposed algorithms in two case studies, where the proposed algorithms show reductions in the computation time by up to four orders of magnitude in comparison with the sampling-based baseline algorithms (for a dataset with 800 sampled trajectories in total).

cs.AI↗

arXiv2021

Temporal-Logic-Based Intermittent, Optimal, and Safe Continuous-Time Learning for Trajectory Tracking

In this paper, we develop safe reinforcement-learning-based controllers for systems tasked with accomplishing complex missions that can be expressed as linear temporal logic specifications, similar to those required by search-and-rescue missions. We decompose the original mission into a sequence of tracking sub-problems under safety constraints. We impose the safety conditions by utilizing barrier functions to map the constrained optimal tracking problem in the physical space to an unconstrained one in the transformed space. Furthermore, we develop policies that intermittently update the control signal to solve the tracking sub-problems with reduced burden in the communication and computation resources. Subsequently, an actor-critic algorithm is utilized to solve the underlying Hamilton-Jacobi-Bellman equations. Finally, we support our proposed framework with stability proofs and showcase its efficacy via simulation results.

eess.SY↗

arXiv2021

Robust Pandemic Control Synthesis with Formal Specifications: A Case Study on COVID-19 Pandemic

Pandemics can bring a range of devastating consequences to public health and the world economy. Identifying the most effective control strategies has been the imperative task all around the world. Various public health control strategies have been proposed and tested against pandemic diseases (e.g., COVID-19). We study two specific pandemic control models: the susceptible, exposed, infectious, recovered (SEIR) model with vaccination control; and the SEIR model with shield immunity control. We express the pandemic control requirement in metric temporal logic (MTL) formulas. We then develop an iterative approach for synthesizing the optimal control strategies with MTL specifications. We provide simulation results in two different scenarios for robust control of the COVID-19 pandemic: one for vaccination control, and another for shield immunity control, with the model parameters estimated from data in Lombardy, Italy. The results show that the proposed synthesis approach can generate control inputs such that the time-varying numbers of individuals in each category (e.g., infectious, immune) satisfy the MTL specifications with robustness against initial state and parameter uncertainties.

eess.SY↗

arXiv2021

Provably Correct Controller Synthesis of Switched Stochastic Systems with Metric Temporal Logic Specifications: A Case Study on Power Systems

In this paper, we present a provably correct controller synthesis approach for switched stochastic control systems with metric temporal logic (MTL) specifications with provable probabilistic guarantees. We first present the stochastic control bisimulation function for switched stochastic control systems, which bounds the trajectory divergence between the switched stochastic control system and its nominal deterministic control system in a probabilistic fashion. We then develop a method to compute optimal control inputs by solving an optimization problem for the nominal trajectory of the deterministic control system with robustness against initial state variations and stochastic uncertainties. We implement our robust stochastic controller synthesis approach on both a four-bus power system and a nine-bus power system under generation loss disturbances, with MTL specifications expressing requirements for the grid frequency deviations, wind turbine generator rotor speed variations and the power flow constraints at different power lines.

eess.SY↗

arXiv2021

Reward Machines for Cooperative Multi-Agent Reinforcement Learning

In cooperative multi-agent reinforcement learning, a collection of agents learns to interact in a shared environment to achieve a common goal. We propose the use of reward machines (RM) -- Mealy machines used as structured representations of reward functions -- to encode the team's task. The proposed novel interpretation of RMs in the multi-agent setting explicitly encodes required teammate interdependencies, allowing the team-level task to be decomposed into sub-tasks for individual agents. We define such a notion of RM decomposition and present algorithmically verifiable conditions guaranteeing that distributed completion of the sub-tasks leads to team behavior accomplishing the original task. This framework for task decomposition provides a natural approach to decentralized learning: agents may learn to accomplish their sub-tasks while observing only their local state and abstracted representations of their teammates. We accordingly propose a decentralized q-learning algorithm. Furthermore, in the case of undiscounted rewards, we use local value functions to derive lower and upper bounds for the global value function corresponding to the team task. Experimental results in three discrete settings exemplify the effectiveness of the proposed RM decomposition approach, which converges to a successful team policy an order of magnitude faster than a centralized learner and significantly outperforms hierarchical and independent q-learning approaches.

cs.MA↗

arXiv2021

Controller Synthesis for Multi-Agent Systems with Intermittent Communication and Metric Temporal Logic Specifications

This paper investigates the controller synthesis problem for a multi-agent system (MAS) with intermittent communication. We adopt a relay-explorer scheme, where a mobile relay agent with absolute position sensors switches among a set of explorers with relative position sensors to provide intermittent state information. We model the MAS as a switched system where the explorers' dynamics can be either fully-actuated or underactuated. The objective of the explorers is to reach approximate consensus to a predetermined goal region. To guarantee the stability of the switched system and the approximate consensus of the explorers, we derive maximum dwell-time conditions to constrain the length of time each explorer goes without state feedback (from the relay agent). Furthermore, the relay agent needs to satisfy practical constraints such as charging its battery and staying in specific regions of interest. Both the maximum dwell-time conditions and these practical constraints can be expressed by metric temporal logic (MTL) specifications. We iteratively compute the optimal control inputs for the relay agent to satisfy the MTL specifications, while guaranteeing stability and approximate consensus of the explorers. We implement the proposed method on a case study with the CoppeliaSim robot simulator.

cs.RO↗

arXiv2021

Magneto-acoustic oscillations observed in a solar plage region

We gave an extensive study for the quasi-periodic perturbations on the time profiles of the line of sight (LOS) magnetic field in 10x10 sub-areas in a solar plage region (corresponds to a facula on the photosphere). The perturbations are found to be associated with enhancement of He I 10830 A absorption in a moss region, which is connected to loops with million-degree plasma. FFT analysis to the perturbations gives a kind of spectrum similar to that of Doppler velocity: a number of discrete periods around 5 minutes. The amplitudes of the magnetic perturbations are found to be proportional to magnetic field strength over these sub-areas. In addition, magnetic perturbations lag behind a quarter of cycle in phase with respect to the p-mode Doppler velocity. We show that the relationships can be well explained with an MHD solution for the magneto-acoustic oscillations in high-\b{eta} plasma. Observational analysis also shows that, for the two regions with the stronger and weaker magnetic field, the perturbations are always anti-phased. All findings show that the magnetic perturbations are actually magneto-acoustic oscillations on the solar surface, the photosphere, powered by p-mode oscillations. The findings may provide a new diagnostic tool for exploring the relationship between magneto-acoustic oscillations and the heating of solar upper atmosphere, as well as their role in helioseismology.

astro-ph.SR↗

arXiv2020

F3RNet: Full-Resolution Residual Registration Network for Deformable Image Registration

Deformable image registration (DIR) is essential for many image-guided therapies. Recently, deep learning approaches have gained substantial popularity and success in DIR. Most deep learning approaches use the so-called mono-stream "high-to-low, low-to-high" network structure, and can achieve satisfactory overall registration results. However, accurate alignments for some severely deformed local regions, which are crucial for pinpointing surgical targets, are often overlooked. Consequently, these approaches are not sensitive to some hard-to-align regions, e.g., intra-patient registration of deformed liver lobes. In this paper, we propose a novel unsupervised registration network, namely the Full-Resolution Residual Registration Network (F3RNet), for deformable registration of severely deformed organs. The proposed method combines two parallel processing streams in a residual learning fashion. One stream takes advantage of the full-resolution information that facilitates accurate voxel-level registration. The other stream learns the deep multi-scale residual representations to obtain robust recognition. We also factorize the 3D convolution to reduce the training parameters and enhance network efficiency. We validate the proposed method on a clinically acquired intra-patient abdominal CT-MRI dataset and a public inspiratory and expiratory thorax CT dataset. Experiments on both multimodal and unimodal registration demonstrate promising results compared to state-of-the-art approaches.

eess.IV↗

arXiv2020

Predicting the Evolution of Photospheric Magnetic Field in Solar Active Regions Using Deep Learning

The continuous observation of the magnetic field by Solar Dynamics Observatory (SDO)/Helioseismic and Magnetic Imager (HMI) produces numerous image sequences in time and space. These sequences provide data support for predicting the evolution of photospheric magnetic field. Based on the spatiotemporal long short-term memory(LSTM) network, we use the preprocessed data of photospheric magnetic field in active regions to build a prediction model for magnetic field evolution. Because of the elaborate learning and memory mechanism, the trained model can characterize the inherent relationships contained in spatiotemporal features. The testing results of the prediction model indicate that (1) the prediction pattern learned by the model can be applied to predict the evolution of new magnetic field in the next 6 hour that have not been trained, and predicted results are roughly consistent with real observed magnetic field evolution in terms of large-scale structure and movement speed; (2) the performance of the model is related to the prediction time; the shorter the prediction time, the higher the accuracy of the predicted results; (3) the performance of the model is stable not only for active regions in the north and south but also for data in positive and negative regions. Detailed experimental results and discussions on magnetic flux emergence and magnetic neutral lines finally show that the proposed model could effectively predict the large-scale and short-term evolution of the photospheric magnetic field in active regions. Moreover, our study may provide a reference for the spatiotemporal prediction of other solar activities.

astro-ph.SR↗

arXiv2020

Unimodal Cyclic Regularization for Training Multimodal Image Registration Networks

The loss function of an unsupervised multimodal image registration framework has two terms, i.e., a metric for similarity measure and regularization. In the deep learning era, researchers proposed many approaches to automatically learn the similarity metric, which has been shown effective in improving registration performance. However, for the regularization term, most existing multimodal registration approaches still use a hand-crafted formula to impose artificial properties on the estimated deformation field. In this work, we propose a unimodal cyclic regularization training pipeline, which learns task-specific prior knowledge from simpler unimodal registration, to constrain the deformation field of multimodal registration. In the experiment of abdominal CT-MR registration, the proposed method yields better results over conventional regularization methods, especially for severely deformed local regions.

cs.CV↗