arXiv subjects

Tianming Wang

Publications and source records attributed to Tianming Wang.

At least 19 recordsLinked to original sources

arXiv2026

Robust Spectral Recovery for Dynamical Sampling

We study the spectral recovery problem for dynamical sampling on a finite cyclic grid. Given time snapshots obtained from a fixed uniform spatial subsampling of the orbit $x_{\ell}=A^{\ell}f$, we aim to recover the spectrum of the unknown circular convolution operator $A$. However, in the presence of outliers, even in only a few snapshots, existing approaches often struggle to recover the spectrum. We address this challenge by proposing a novel robust spectral recovery model in the presence of time-sparse corruptions. We propose a robust pipeline that lifts the problem to a sequence of robust low-rank Hankel recovery and completion tasks, followed by Prony-type spectral estimation. Numerical experiments confirm the accurate spectral recovery of the proposed approach and exhibit its superior robustness against state-of-the-art under various settings.

cs.IT↗

arXiv2026

Fast and Provable Nonconvex Robust Matrix Completion

We study the robust matrix completion (RMC) problem subject to both sparse outliers and stochastic noise. A non-convex method termed Accelerated Robust Matrix Completion (ARMC) is proposed, which accelerates a prior non-convex approach by incorporating an explicit subspace projection step into the low-rank update, leading to significantly improved computational efficiency. Through a delicate analysis based on the leave-one-out technique, the entrywise linear convergence guarantee of ARMC has been established. Notably, the derived bounds for sample complexity and outlier sparsity improve upon existing guarantees of the convex relaxation approach that also accounts for both sparse outliers and stochastic noise. Moreover, numerical experiments on synthetic and real data show that ARMC is superior to existing non-convex RMC methods.

cs.IT↗

arXiv2025

A Social Force Model for Companion Groups Considering Relative-Weight Attraction

This paper introduces an improved social force model for companion group that incorporates relative weight attraction. Based on the traditional social force model, the interaction forces among individuals within leader-follower groups are described by introducing relative weight attraction. Additionally, a velocity synchronization term is integrated into the pedestrians' self-driving force to address the problem of group dispersion commonly found in traditional models. Furthermore, the desired direction of followers within the companion group is refined to adapt to the evacuation movement led by the group leader. These enhancements collectively form a Social Force Model of companion groups considering relative weight attraction. Through comparative analysis of pedestrian evacuation processes in bidirectional channel simulation experiments between the relative weight attraction model and the traditional molecular potential (force) model, this study finds that the relative weight attraction model demonstrates stronger regulation and following capabilities when simulating collisions between companion groups and pedestrians or obstacles, more effectively ensuring group cohesion. Building upon this foundation, this study further investigates the impact of varying companion ratios on evacuation efficiency within the relative-weight attraction model. The results demonstrate that evacuation time steps exhibit a non-monotonic trend (initial increase, followed by a decrease, and a subsequent rise) as the companion ratio escalates. Additionally, across multiple simulation runs, the standard deviation of evacuation time steps expands with increasing companion ratios, indicating heightened fluctuation in individual evacuation timing.

physics.soc-ph↗

arXiv2025

Robust Multi-Dimensional Scaling via Accelerated Alternating Projections

We consider the robust multi-dimensional scaling (RMDS) problem in this paper. The goal is to localize point locations from pairwise distances that may be corrupted by outliers. Inspired by classic MDS theories, and nonconvex works for the robust principal component analysis (RPCA) problem, we propose an alternating projection based algorithm that is further accelerated by the tangent space projection technique. For the proposed algorithm, if the outliers are sparse enough, we can establish linear convergence of the reconstructed points to the original points after centering and rotation alignment. Numerical experiments verify the state-of-the-art performances of the proposed algorithm.

stat.ML↗

arXiv2024

Leave-One-Out Analysis for Nonconvex Robust Matrix Completion with General Thresholding Functions

We study the problem of robust matrix completion (RMC), where the partially observed entries of an underlying low-rank matrix is corrupted by sparse noise. Existing analysis of the non-convex methods for this problem either requires the explicit but empirically redundant regularization in the algorithm or requires sample splitting in the analysis. In this paper, we consider a simple yet efficient nonconvex method which alternates between a projected gradient step for the low-rank part and a thresholding step for the sparse noise part. Inspired by leave-one out analysis for low rank matrix completion, it is established that the method can achieve linear convergence for a general class of thresholding functions, including for example soft-thresholding and SCAD. To the best of our knowledge, this is the first leave-one-out analysis on a nonconvex method for RMC. Additionally, when applying our result to low rank matrix completion, it improves the sampling complexity of existing result for the singular value projection method.

cs.IT↗

arXiv2023

Outlier Detection Using Generative Models with Theoretical Performance Guarantees

This paper considers the problem of recovering signals modeled by generative models from linear measurements contaminated with sparse outliers. We propose an outlier detection approach for reconstructing the ground-truth signals modeled by generative models under sparse outliers. We establish theoretical recovery guarantees for reconstruction of signals using generative models in the presence of outliers, giving lower bounds on the number of correctable outliers. Our results are applicable to both linear generator neural networks and the nonlinear generator neural networks with an arbitrary number of layers. We propose an iterative alternating direction method of multipliers (ADMM) algorithm for solving the outlier detection problem via $\ell_1$ norm minimization, and a gradient descent algorithm for solving the outlier detection problem via squared $\ell_1$ norm minimization. We conduct extensive experiments using variational auto-encoder and deep convolutional generative adversarial networks, and the experimental results show that the signals can be successfully reconstructed under outliers using our approach. Our approach outperforms the traditional Lasso and $\ell_2$ minimization approach.

stat.ML↗

arXiv2023

Continual Transfer Learning for Cross-Domain Click-Through Rate Prediction at Taobao

As one of the largest e-commerce platforms in the world, Taobao's recommendation systems (RSs) serve the demands of shopping for hundreds of millions of customers. Click-Through Rate (CTR) prediction is a core component of the RS. One of the biggest characteristics in CTR prediction at Taobao is that there exist multiple recommendation domains where the scales of different domains vary significantly. Therefore, it is crucial to perform cross-domain CTR prediction to transfer knowledge from large domains to small domains to alleviate the data sparsity issue. However, existing cross-domain CTR prediction methods are proposed for static knowledge transfer, ignoring that all domains in real-world RSs are continually time-evolving. In light of this, we present a necessary but novel task named Continual Transfer Learning (CTL), which transfers knowledge from a time-evolving source domain to a time-evolving target domain. In this work, we propose a simple and effective CTL model called CTNet to solve the problem of continual cross-domain CTR prediction at Taobao, and CTNet can be trained efficiently. Particularly, CTNet considers an important characteristic in the industry that models has been continually well-trained for a very long time. So CTNet aims to fully utilize all the well-trained model parameters in both source domain and target domain to avoid losing historically acquired knowledge, and only needs incremental target domain data for training to guarantee efficiency. Extensive offline experiments and online A/B testing at Taobao demonstrate the efficiency and effectiveness of CTNet. CTNet is now deployed online in the recommender systems of Taobao, serving the main traffic of hundreds of millions of active users.

cs.IR↗

arXiv2022

An End-to-End Cascaded Image Deraining and Object Detection Neural Network

While the deep learning-based image deraining methods have made great progress in recent years, there are two major shortcomings in their application in real-world situations. Firstly, the gap between the low-level vision task represented by rain removal and the high-level vision task represented by object detection is significant, and the low-level vision task can hardly contribute to the high-level vision task. Secondly, the quality of the deraining dataset needs to be improved. In fact, the rain lines in many baselines have a large gap with the real rain lines, and the resolution of the deraining dataset images is generally not ideally. Meanwhile, there are few common datasets for both the low-level vision task and the high-level vision task. In this paper, we explore the combination of the low-level vision task with the high-level vision task. Specifically, we propose an end-to-end object detection network for reducing the impact of rainfall, which consists of two cascaded networks, an improved image deraining network and an object detection network, respectively. We also design the components of the loss function to accommodate the characteristics of the different sub-networks. We then propose a dataset based on the KITTI dataset for rainfall removal and object detection, on which our network surpasses the state-of-the-art with a significant improvement in metrics. Besides, our proposed network is measured on driving videos collected by self-driving vehicles and shows positive results for rain removal and object detection.

cs.CV↗

arXiv2021

Accelerated Structured Alternating Projections for Robust Spectrally Sparse Signal Recovery

Consider a spectrally sparse signal $\boldsymbol{x}$ that consists of $r$ complex sinusoids with or without damping. We study the robust recovery problem for the spectrally sparse signal under the fully observed setting, which is about recovering $\boldsymbol{x}$ and a sparse corruption vector $\boldsymbol{s}$ from their sum $\boldsymbol{z}=\boldsymbol{x}+\boldsymbol{s}$. In this paper, we exploit the low-rank property of the Hankel matrix formed by $\boldsymbol{x}$, and formulate the problem as the robust recovery of a corrupted low-rank Hankel matrix. We develop a highly efficient non-convex algorithm, coined Accelerated Structured Alternating Projections (ASAP). The high computational efficiency and low space complexity of ASAP are achieved by fast computations involving structured matrices, and a subspace projection method for accelerated low-rank approximation. Theoretical recovery guarantee with a linear convergence rate has been established for ASAP, under some mild assumptions on $\boldsymbol{x}$ and $\boldsymbol{s}$. Empirical performance comparisons on both synthetic and real-world data confirm the advantages of ASAP, in terms of computational efficiency and robustness aspects.

cs.IT↗

arXiv2020

Modular Transfer Learning with Transition Mismatch Compensation for Excessive Disturbance Rejection

Underwater robots in shallow waters usually suffer from strong wave forces, which may frequently exceed robot's control constraints. Learning-based controllers are suitable for disturbance rejection control, but the excessive disturbances heavily affect the state transition in Markov Decision Process (MDP) or Partially Observable Markov Decision Process (POMDP). Also, pure learning procedures on targeted system may encounter damaging exploratory actions or unpredictable system variations, and training exclusively on a prior model usually cannot address model mismatch from the targeted system. In this paper, we propose a transfer learning framework that adapts a control policy for excessive disturbance rejection of an underwater robot under dynamics model mismatch. A modular network of learning policies is applied, composed of a Generalized Control Policy (GCP) and an Online Disturbance Identification Model (ODI). GCP is first trained over a wide array of disturbance waveforms. ODI then learns to use past states and actions of the system to predict the disturbance waveforms which are provided as input to GCP (along with the system state). A transfer reinforcement learning algorithm using Transition Mismatch Compensation (TMC) is developed based on the modular architecture, that learns an additional compensatory policy through minimizing mismatch of transitions predicted by the two dynamics models of the source and target tasks. We demonstrated on a pose regulation task in simulation that TMC is able to successfully reject the disturbances and stabilize the robot under an empirical model of the robot system, meanwhile improve sample efficiency.

cs.RO↗

arXiv2020

DOB-Net: Actively Rejecting Unknown Excessive Time-Varying Disturbances

This paper presents an observer-integrated Reinforcement Learning (RL) approach, called Disturbance OBserver Network (DOB-Net), for robots operating in environments where disturbances are unknown and time-varying, and may frequently exceed robot control capabilities. The DOB-Net integrates a disturbance dynamics observer network and a controller network. Originated from conventional DOB mechanisms, the observer is built and enhanced via Recurrent Neural Networks (RNNs), encoding estimation of past values and prediction of future values of unknown disturbances in RNN hidden state. Such encoding allows the controller generate optimal control signals to actively reject disturbances, under the constraints of robot control capabilities. The observer and the controller are jointly learned within policy optimization by advantage actor critic. Numerical simulations on position regulation tasks have demonstrated that the proposed DOB-Net significantly outperforms a conventional feedback controller and classical RL algorithms.

cs.RO↗

arXiv2020

Effects of free-ranging livestock on sympatric herbivores at fine spatiotemporal scales

Understanding wildlife-livestock interactions is crucial for the design and management of protected areas that aim to conserve large mammal communities undergoing conflicts with humans worldwide. An example of the need to quantify the strength and direction of species interactions is the conservation of big cats in newly established protected areas in China. Currently, free-ranging livestock degrade the food and habitat of the endangered Amur tiger and Amur leopard in the forest landscapes of Northeast China, but quantitative assessments of how livestock affect the use of habitat by the major ungulate prey of these predators are very limited. Here, we examined livestock-ungulate interactions using large-scale camera-trap data in the newly established Tiger and Leopard National Park in Northeast China, which borders Russia. We used N-mixture models, two-species occupancy models and activity pattern overlap to understand the effects of cattle grazing on three ungulate species (wild boar, roe deer and sika deer) at a fine spatiotemporal scale. Our results showed that incorporating the biotic interactions with cattle had significant negative effects on encounters with three ungulates; sika deer were particularly displaced as more cattle encroached on forest habitat, as they exhibited low levels of co-occurrence with cattle in terms of habitat use. These results, combined with spatiotemporal overlap, suggested fine-scale avoidance behaviours, and they can help to refine strategies for the conservation of tigers, leopards and their prey in human-dominated transboundary landscapes. Progressively controlling cattle and the impact of cattle on biodiversity while simultaneously addressing the economic needs of local communities should be key priority actions for the Chinese government.

q-bio.PE↗

arXiv2020

Fast Cadzow's Algorithm and a Gradient Variant

The Cadzow's algorithm is a signal denoising and recovery method which was designed for signals corresponding to low rank Hankel matrices. In this paper we first introduce a Fast Cadzow's algorithm which is developed by incorporating a novel subspace projection to reduce the high computational cost of the SVD in the Cadzow's algorithm. Then a Gradient method and a Fast Gradient method are proposed to address the non-decreasing MSE issue when applying the Cadzow's or Fast Cadzow's algorithm for signal denoising. Extensive empirical performance comparisons demonstrate that the proposed algorithms can complete the denoising and recovery tasks more efficiently and effectively.

math.NA↗

arXiv2019

SketchyCoreSVD: SketchySVD from Random Subsampling of the Data Matrix

We present a method called SketchyCoreSVD to compute the near-optimal rank r SVD of a data matrix by building random sketches only from its subsampled columns and rows. We provide theoretical guarantees under incoherence assumptions, and validate the performance of our SketchyCoreSVD method on various large static and time-varying datasets.

math.NA↗

arXiv2019

Prey selection of Amur tigers in relation to the spatiotemporal overlap with prey across the Sino-Russian border

The endangered Amur tiger is confined primarily to a narrow area along the border with Russia in Northeast China. Little is known about the foraging strategies of this small subpopulation in Hunchun Nature Reserve on the Chinese side of the border; at this location, the prey base and land use patterns are distinctly different from those in the larger population of the Sikhote-Alin Mountains of Russia. Using dietary analysis of scats and camera-trapping data from Hunchun Nature Reserve, we assessed spatiotemporal overlap of tigers and their prey and identified prey selection patterns to enhance understanding of the ecological requirements of tigers in Northeast China. Results indicated that wild prey constituted 94.9% of the total biomass consumed by tigers; domestic livestock represented 5.1% of the diet. Two species, wild boar and sika deer , collectively represented 83% of the biomass consumed by tigers. Despite lower spatial overlap of tigers and wild boar compared to tigers and sika deer, tigers preferentially preyed on boar, likely facilitated by high temporal overlap in activity patterns. Tigers exhibit significant spatial overlap with sika deer, likely favoring a high level of tiger predation on this large-sized ungulate. However, tigers did not preferred roe deer (Capreolus pygargus) and showed a low spatial overlap with roe deer. Overall, our results suggest that tiger prey selection is determined by prey body size and also overlap in tiger and prey use of time or space. Also, we suggest that strategies designed to minimize livestock forays into forested lands may be important for decreasing the livestock depredation by tigers. This study offers a framework to simultaneously integrate food habit analysis with the distribution of predators and prey through time and space to provide a comprehensive understanding of foraging strategies of large carnivores.

q-bio.PE↗

arXiv2019

Blind Hyperspectral-Multispectral Image Fusion via Graph Laplacian Regularization

Fusing a low-resolution hyperspectral image (HSI) and a high-resolution multispectral image (MSI) of the same scene leads to a super-resolution image (SRI), which is information rich spatially and spectrally. In this paper, we super-resolve the HSI using the graph Laplacian defined on the MSI. Unlike many existing works, we don't assume prior knowledge about the spatial degradation from SRI to HSI, nor a perfectly aligned HSI and MSI pair. Our algorithm progressively alternates between finding the blur kernel and fusing HSI with MSI, generating accurate estimations of the blur kernel and the SRI at convergence. Experiments on various datasets demonstrate the advantages of the proposed algorithm in the quality of fusion and its capability in dealing with unknown spatial degradation.

cs.CV↗

arXiv2018

Outlier Detection using Generative Models with Theoretical Performance Guarantees

This paper considers the problem of recovering signals from compressed measurements contaminated with sparse outliers, which has arisen in many applications. In this paper, we propose a generative model neural network approach for reconstructing the ground truth signals under sparse outliers. We propose an iterative alternating direction method of multipliers (ADMM) algorithm for solving the outlier detection problem via $\ell_1$ norm minimization, and a gradient descent algorithm for solving the outlier detection problem via squared $\ell_1$ norm minimization. We establish the recovery guarantees for reconstruction of signals using generative models in the presence of outliers, and give an upper bound on the number of outliers allowed for recovery. Our results are applicable to both the linear generator neural network and the nonlinear generator neural network with an arbitrary number of layers. We conduct extensive experiments using variational auto-encoder and deep convolutional generative adversarial networks, and the experimental results show that the signals can be successfully reconstructed under outliers using our approach. Our approach outperforms the traditional Lasso and $\ell_2$ minimization approach.

cs.IT↗

arXiv2017

Spectral Compressed Sensing via Projected Gradient Descent

Let $x\in\mathbb{C}^n$ be a spectrally sparse signal consisting of $r$ complex sinusoids with or without damping. We consider the spectral compressed sensing problem, which is about reconstructing $x$ from its partial revealed entries. By utilizing the low rank structure of the Hankel matrix corresponding to $x$, we develop a computationally efficient algorithm for this problem. The algorithm starts from an initial guess computed via one-step hard thresholding followed by projection, and then proceeds by applying projected gradient descent iterations to a non-convex functional. Based on the sampling with replacement model, we prove that $O(r^2\log(n))$ observed entries are sufficient for our algorithm to achieve the successful recovery of a spectrally sparse signal. Moreover, extensive empirical performance comparisons show that our algorithm is competitive with other state-of-the-art spectral compressed sensing algorithms in terms of phase transitions and overall computational time.

math.OC↗