arXiv subjects

Wei Pan

Publications and source records attributed to Wei Pan.

At least 181 records · Page 10Linked to original sources

arXiv2020

Dynamic Network Reconstruction from Heterogeneous Datasets

Performing multiple experiments is common when learning internal mechanisms of complex systems. These experiments can include perturbations to parameters or external disturbances. A challenging problem is to efficiently incorporate all collected data simultaneously to infer the underlying dynamic network. This paper addresses the reconstruction of dynamic networks from heterogeneous datasets under the assumption that underlying networks share the same Boolean structure across all experiments. Parametric models for dynamical structure functions are derived to describe causal interactions between measured variables. Multiple datasets are integrated into one regression problem with additional demands of group sparsity to assure network sparsity and structure consistency. To acquire structured group sparsity, we propose a sampling-based method, together with extended versions of l1 methods and sparse Bayesian learning. The performance of the proposed methods is benchmarked in numerical simulation. In summary, this paper presents efficient methods on network reconstruction from multiple experiments, and reveals practical experience that could guide applications.

eess.SY↗

arXiv2020

A Particle Filter for Stochastic Advection by Lie Transport (SALT): A case study for the damped and forced incompressible 2D Euler equation

In this work, we combine a stochastic model reduction with a particle filter augmented with tempering and jittering, and apply the combined algorithm to a damped and forced incompressible 2D Euler dynamics defined on a simply connected bounded domain. We show that using the combined algorithm, we are able to assimilate data from a reference system state (the ``truth") modelled by a highly resolved numerical solution of the flow that has roughly $3.1\times10^6$ degrees of freedom, into a stochastic system having two orders of magnitude less degrees of freedom, which is able to approximate the true state reasonably accurately for $5$ large scale eddy turnover times, using modest computational hardware. The model reduction is performed through the introduction of a stochastic advection by Lie transport (SALT) model as the signal on a coarser resolution. The SALT approach was introduced as a general theory using a geometric mechanics framework from Holm, Proc. Roy. Soc. A (2015). This work follows on the numerical implementation for SALT presented by Cotter et al, SIAM Multiscale Model. Sim. (2019) for the flow in consideration. The model reduction is substantial: The reduced SALT model has $4.9\times 10^4$ degrees of freedom. Results from reliability tests on the assimilated system are also presented.

stat.AP↗

arXiv2020

Model-Reference Reinforcement Learning for Collision-Free Tracking Control of Autonomous Surface Vehicles

This paper presents a novel model-reference reinforcement learning algorithm for the intelligent tracking control of uncertain autonomous surface vehicles with collision avoidance. The proposed control algorithm combines a conventional control method with reinforcement learning to enhance control accuracy and intelligence. In the proposed control design, a nominal system is considered for the design of a baseline tracking controller using a conventional control approach. The nominal system also defines the desired behaviour of uncertain autonomous surface vehicles in an obstacle-free environment. Thanks to reinforcement learning, the overall tracking controller is capable of compensating for model uncertainties and achieving collision avoidance at the same time in environments with obstacles. In comparison to traditional deep reinforcement learning methods, our proposed learning-based control can provide stability guarantees and better sample efficiency. We demonstrate the performance of the new algorithm using an example of autonomous surface vehicles.

eess.SY↗

arXiv2020

$H_\infty$ Model-free Reinforcement Learning with Robust Stability Guarantee

Reinforcement learning is showing great potentials in robotics applications, including autonomous driving, robot manipulation and locomotion. However, with complex uncertainties in the real-world environment, it is difficult to guarantee the successful generalization and sim-to-real transfer of learned policies theoretically. In this paper, we introduce and extend the idea of robust stability and $H_\infty$ control to design policies with both stability and robustness guarantee. Specifically, a sample-based approach for analyzing the Lyapunov stability and performance robustness of a learning-based control system is proposed. Based on the theoretical results, a maximum entropy algorithm is developed for searching Lyapunov function and designing a policy with provable robust stability guarantee. Without any specific domain knowledge, our method can find a policy that is robust to various uncertainties and generalizes well to different test environments. In our experiments, we show that our method achieves better robustness to both large impulsive disturbances and parametric variations in the environment than the state-of-art results in both robust and generic RL, as well as classic control. Anonymous code is available to reproduce the experimental results at https://github.com/RobustStabilityGuaranteeRL/RobustStabilityGuaranteeRL.

cs.LG↗

arXiv2020

Actor-Critic Reinforcement Learning for Control with Stability Guarantee

Reinforcement Learning (RL) and its integration with deep learning have achieved impressive performance in various robotic control tasks, ranging from motion planning and navigation to end-to-end visual manipulation. However, stability is not guaranteed in model-free RL by solely using data. From a control-theoretic perspective, stability is the most important property for any control system, since it is closely related to safety, robustness, and reliability of robotic systems. In this paper, we propose an actor-critic RL framework for control which can guarantee closed-loop stability by employing the classic Lyapunov's method in control theory. First of all, a data-based stability theorem is proposed for stochastic nonlinear systems modeled by Markov decision process. Then we show that the stability condition could be exploited as the critic in the actor-critic RL to learn a controller/policy. At last, the effectiveness of our approach is evaluated on several well-known 3-dimensional robot control tasks and a synthetic biology gene network tracking task in three different popular physics simulation platforms. As an empirical evaluation on the advantage of stability, we show that the learned policies can enable the systems to recover to the equilibrium or way-points when interfered by uncertainties such as system parametric variations and external disturbances to a certain extent.

cs.RO↗

arXiv2020

Modelling uncertainty using stochastic transport noise in a 2-layer quasi-geostrophic model

The stochastic variational approach for geophysical fluid dynamics was introduced by Holm (Proc Roy Soc A, 2015) as a framework for deriving stochastic parameterisations for unresolved scales. This paper applies the variational stochastic parameterisation in a two-layer quasi-geostrophic model for a beta-plane channel flow configuration. We present a new method for estimating the stochastic forcing (used in the parameterisation) to approximate unresolved components using data from the high resolution deterministic simulation, and describe a procedure for computing physically-consistent initial conditions for the stochastic model. We also quantify uncertainty of coarse grid simulations relative to the fine grid ones in homogeneous (teamed with small-scale vortices) and heterogeneous (featuring horizontally elongated large-scale jets) flows, and analyse how the spread of stochastic solutions depends on different parameters of the model. The parameterisation is tested by comparing it with the true eddy-resolving solution that has reached some statistical equilibrium and the deterministic solution modelled on a low-resolution grid. The results show that the proposed parameterisation significantly depends on the resolution of the stochastic model and gives good ensemble performance for both homogeneous and heterogeneous flows, and the parameterisation lays solid foundations for data assimilation.

physics.flu-dyn↗

arXiv2020

Model-Reference Reinforcement Learning Control of Autonomous Surface Vehicles with Uncertainties

This paper presents a novel model-reference reinforcement learning control method for uncertain autonomous surface vehicles. The proposed control combines a conventional control method with deep reinforcement learning. With the conventional control, we can ensure the learning-based control law provides closed-loop stability for the overall system, and potentially increase the sample efficiency of the deep reinforcement learning. With the reinforcement learning, we can directly learn a control law to compensate for modeling uncertainties. In the proposed control, a nominal system is employed for the design of a baseline control law using a conventional control approach. The nominal system also defines the desired performance for uncertain autonomous vehicles to follow. In comparison with traditional deep reinforcement learning methods, our proposed learning-based control can provide stability guarantees and better sample efficiency. We demonstrate the performance of the new algorithm via extensive simulation results.

eess.SY↗

arXiv2020

Establishing simple relationship between eigenvector and matrix elements

A simple approximate relationship between the ground-state eigenvector and the sum of matrix elements in each row has been established for real symmetric matrices with non-positive off-diagonal elements. Specifically, the $i$-th components of the ground-state eigenvector could be calculated by $(-S_i)^p+c$, where $S_i$ is the sum of elements in the $i$-th row of the matrix with $p$ and $c$ being variational parameters. The simple relationship provides a straightforward method to directly calculate the ground-state eigenvector for a matrix. Our preliminary applications to the Hubbard model and the Ising model in a transverse field show encouraging results.The simple relationship also provide the optimal initial state for other more accurate methods, such as the Lanczos method.

cond-mat.mes-hall↗

arXiv2020

Asymptotically Independent U-Statistics in High-Dimensional Testing

Many high-dimensional hypothesis tests aim to globally examine marginal or low-dimensional features of a high-dimensional joint distribution, such as testing of mean vectors, covariance matrices and regression coefficients. This paper constructs a family of U-statistics as unbiased estimators of the $\ell_p$-norms of those features. We show that under the null hypothesis, the U-statistics of different finite orders are asymptotically independent and normally distributed. Moreover, they are also asymptotically independent with the maximum-type test statistic, whose limiting distribution is an extreme value distribution. Based on the asymptotic independence property, we propose an adaptive testing procedure which combines $p$-values computed from the U-statistics of different orders. We further establish power analysis results and show that the proposed adaptive procedure maintains high power against various alternatives.

math.ST↗

arXiv2020

HLO: Half-kernel Laplacian Operator for Surface Smoothing

This paper presents a simple yet effective method for feature-preserving surface smoothing. Through analyzing the differential property of surfaces, we show that the conventional discrete Laplacian operator with uniform weights is not applicable to feature points at which the surface is non-differentiable and the second order derivatives do not exist. To overcome this difficulty, we propose a Half-kernel Laplacian Operator (HLO) as an alternative to the conventional Laplacian. Given a vertex v, HLO first finds all pairs of its neighboring vertices and divides each pair into two subsets (called half windows); then computes the uniform Laplacians of all such subsets and subsequently projects the computed Laplacians to the full-window uniform Laplacian to alleviate flipping and degeneration. The half window with least regularization energy is then chosen for v. We develop an iterative approach to apply HLO for surface denoising. Our method is conceptually simple and easy to use because it has a single parameter, i.e., the number of iterations for updating vertices. We show that our method can preserve features better than the popular uniform Laplacian-based denoising and it significantly alleviates the shrinkage artifact. Extensive experimental results demonstrate that HLO is better than or comparable to state-of-the-art techniques both qualitatively and quantitatively and that it is particularly good at handling meshes with high noise. We will make our source code publicly available.

cs.CG↗

arXiv2019

A Sparse Bayesian Deep Learning Approach for Identification of Cascaded Tanks Benchmark

Nonlinear system identification is important with a wide range of applications. The typical approaches for nonlinear system identification include Volterra series models, nonlinear autoregressive with exogenous inputs models, block-structured models, state-space models and neural network models. Among them, neural networks (NN) is an important black-box method thanks to its universal approximation capability and less dependency on prior information. However, there are several challenges associated with NN. The first one lies in the design of a proper neural network structure. A relatively simple network cannot approximate the feature of the system, while a complex model may lead to overfitting. The second lies in the availability of data for some nonlinear systems. For some systems, it is difficult to collect enough data to train a neural network. This raises the challenge that how to train a neural network for system identification with a small dataset. In addition, if the uncertainty of the NN parameter could be obtained, it would be also beneficial for further analysis. In this paper, we propose a sparse Bayesian deep learning approach to address the above problems. Specifically, the Bayesian method can reinforce the regularization on neural networks by introducing introduced sparsity-inducing priors. The Bayesian method can also compute the uncertainty of the NN parameter. An efficient iterative re-weighted algorithm is presented in this paper. We also test the capacity of our method to identify the system on various ratios of the original dataset. The one-step-ahead prediction experiment on Cascaded Tank System shows the effectiveness of our method. Furthermore, we test our algorithm with more challenging simulation experiment on this benchmark, which also outperforms other methods.

eess.SY↗

arXiv2019

Data assimilation for a quasi-geostrophic model with circulation-preserving stochastic transport noise

This paper contains the latest installment of the authors' project on developing ensemble based data assimilation methodology for high dimensional fluid dynamics models. The algorithm presented here is a particle filter that combines model reduction, tempering, jittering, and nudging. The methodology is tested on a two-layer quasi-geostrophic model for a $β$-plane channel flow with $O(10^6)$ degrees of freedom out of which only a minute fraction are noisily observed. The model is reduced by following the stochastic variational approach for geophysical fluid dynamics introduced in Holm (Proc Roy Soc A, 2015) as a framework for deriving stochastic parametrisations for unresolved scales. The reduction is substantial: the computations are done only for $O(10^4)$ degrees of freedom. We introduce a stochastic time-stepping scheme for the two-layer model and prove its consistency in time. Then, we analyze the effect of the different procedures (tempering combined with jittering and nudging) on the performance of the data assimilation procedure using the reduced model, as well as how the dimension of the observational data (the number of "weather stations") and the data assimilation step affect the accuracy and uncertainty of the results.

math.NA↗

arXiv2019

BayesNAS: A Bayesian Approach for Neural Architecture Search

One-Shot Neural Architecture Search (NAS) is a promising method to significantly reduce search time without any separate training. It can be treated as a Network Compression problem on the architecture parameters from an over-parameterized network. However, there are two issues associated with most one-shot NAS methods. First, dependencies between a node and its predecessors and successors are often disregarded which result in improper treatment over zero operations. Second, architecture parameters pruning based on their magnitude is questionable. In this paper, we employ the classic Bayesian learning approach to alleviate these two issues by modeling architecture parameters using hierarchical automatic relevance determination (HARD) priors. Unlike other NAS methods, we train the over-parameterized network for only one epoch then update the architecture. Impressively, this enabled us to find the architecture on CIFAR-10 within only 0.2 GPU days using a single GPU. Competitive performance can be also achieved by transferring to ImageNet. As a byproduct, our approach can be applied directly to compress convolutional neural networks by enforcing structural sparsity which achieves extremely sparse networks without accuracy deterioration.

cs.LG↗

arXiv2019

A new strategy for directly calculating the minimum eigenvector of matrices without diagonalization

The diagonalization of matrices may be the top priority in the application of modern physics. In this paper, we numerically demonstrate that, for real symmetric random matrices with non-positive off-diagonal elements, a universal scaling between the eigenvector and matrix elements exists. Namely, each element of the eigenvector of ground states linearly correlates with the sum of matrix elements in the corresponding row. Although the conclusion is obtained based on the random matrices, the linear relationship still keeps for regular matrices, in which off-diagonal elements are non-positive. The relationship implies a straightforward method to directly calculate the eigenvector of ground states for a kind of matrices. The test on both Hubbard and Ising models shows that, this new method works excellently.

quant-ph↗

arXiv2019

Multifunctional photonic integrated circuit for diverse microwave signal generation, transmission and processing

Microwave photonics (MWP) studies the interaction between microwave and optical waves for the generation, transmission and processing of microwave signals (i.e., three key domains), taking advantages of broad bandwidth and low loss offered by modern photonics. Integrated MWP using photonic integrated circuits (PICs) can reach a compact, reliable and green implementation. Most PICs, however, are recently developed to perform one or more functions restricted inside a single domain. In this paper, as highly desired, a multifunctional PIC is proposed to cover the three key domains. The PIC is fabricated on InP platform by monolithically integrating four laser diodes and two modulators. Using the multifunctional PIC, seven fundamental functions across microwave signal generation, transmission and processing are demonstrated experimentally. Outdoor field trials for electromagnetic environment surveillance along an in-service high-speed railway are also performed. The success to such a PIC marks a key step forward for practical and massive MWP implementations.

physics.app-ph↗

arXiv2019

Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning

Humans are capable of attributing latent mental contents such as beliefs or intentions to others. The social skill is critical in daily life for reasoning about the potential consequences of others' behaviors so as to plan ahead. It is known that humans use such reasoning ability recursively by considering what others believe about their own beliefs. In this paper, we start from level-$1$ recursion and introduce a probabilistic recursive reasoning (PR2) framework for multi-agent reinforcement learning. Our hypothesis is that it is beneficial for each agent to account for how the opponents would react to its future behaviors. Under the PR2 framework, we adopt variational Bayes methods to approximate the opponents' conditional policies, to which each agent finds the best response and then improve their own policies. We develop decentralized-training-decentralized-execution algorithms, namely PR2-Q and PR2-Actor-Critic, that are proved to converge in the self-play scenarios when there exists one Nash equilibrium. Our methods are tested on both the matrix game and the differential game, which have a non-trivial equilibrium where common gradient-based methods fail to converge. Our experiments show that it is critical to reason about how the opponents believe about what the agent believes. We expect our work to contribute a new idea of modeling the opponents to the multi-agent reinforcement learning community.

cs.LG↗

arXiv2018

Fractional Josephson Effect: A Missing Step Is A Key Step

Physicists are searching for superconducting materials that can host Majoranas. New evidence for these elusive particles is provided by missing Shapiro steps in a Josephson effect mediated by an accidental Dirac semimetal.

cond-mat.supr-con↗

arXiv2018

Data-driven Discovery of Cyber-Physical Systems

Cyber-physical systems (CPSs) embed software into the physical world. They appear in a wide range of applications such as smart grids, robotics, intelligent manufacture and medical monitoring. CPSs have proved resistant to modeling due to their intrinsic complexity arising from the combination of physical components and cyber components and the interaction between them. This study proposes a general framework for reverse engineering CPSs directly from data. The method involves the identification of physical systems as well as the inference of transition logic. It has been applied successfully to a number of real-world examples ranging from mechanical and electrical systems to medical applications. The novel framework seeks to enable researchers to make predictions concerning the trajectory of CPSs based on the discovered model. Such information has been proven essential for the assessment of the performance of CPS, the design of failure-proof CPS and the creation of design guidelines for new CPSs.

eess.SY↗