Searcharxiv⌕ Search

arXiv subjects

Yang Zheng

Publications and source records attributed to Yang Zheng.

At least 91 records · Page 5Linked to original sources
arXiv2024

Enhancing Distributional Stability among Sub-populations

Enhancing the stability of machine learning algorithms under distributional shifts is at the heart of the Out-of-Distribution (OOD) Generalization problem. Derived from causal learning, recent works of invariant learning pursue strict invariance with multiple training environments. Although intuitively reasonable, strong assumptions on the availability and quality of environments are made to learn the strict invariance property. In this work, we come up with the ``distributional stability" notion to mitigate such limitations. It quantifies the stability of prediction mechanisms among sub-populations down to a prescribed scale. Based on this, we propose the learnability assumption and derive the generalization error bound under distribution shifts. Inspired by theoretical analyses, we propose our novel stable risk minimization (SRM) algorithm to enhance the model's stability w.r.t. shifts in prediction mechanisms ($Y|X$-shifts). Experimental results are consistent with our intuition and validate the effectiveness of our algorithm. The code can be found at https://github.com/LJSthu/SRM.

cs.LG↗
arXiv2024

Predicting Strategic Energy Storage Behaviors

Energy storage are strategic participants in electricity markets to arbitrage price differences. Future power system operators must understand and predict strategic storage arbitrage behaviors for market power monitoring and capacity adequacy planning. This paper proposes a novel data-driven approach that incorporates prior model knowledge for predicting the strategic behaviors of price-taker energy storage systems. We propose a gradient-descent method to find the storage model parameters given the historical price signals and observations. We prove that the identified model parameters will converge to the true user parameters under a class of quadratic objective and linear equality-constrained storage models. We demonstrate the effectiveness of our approach through numerical experiments with synthetic and real-world storage behavior data. The proposed approach significantly improves the accuracy of storage model identification and behavior forecasting compared to previous blackbox data-driven approaches.

eess.SY↗
arXiv2024

On equivalence relations induced by Polish groups admitting compatible two-sided invariant metrics

Given a Polish group $G$, let $E(G)$ be the right coset equivalence relation $G^ω/c(G)$, where $c(G)$ is the group of all convergent sequences in $G$. We first established two results: (1) Let $G,H$ be two Polish groups. If $H$ is TSI but $G$ is not, then $E(G)\not\le_BE(H)$. (2) Let $G$ be a Polish group. Then the following are equivalent: (a) $G$ is TSI non-archimedean; (b)$E(G)\leq_B E_0^ω$; and (c) $E(G)\leq_B{\mathbb R}^ω/c_0$. In particular, $E(G)\sim_B E_0^ω$ iff $G$ is TSI uncountable non-archimedean. A critical theorem presented in this article is as follows: Let $G$ be a TSI Polish group, and let $H$ be a closed subgroup of the product of a sequence of TSI strongly NSS Polish groups. If $E(G)\le_BE(H)$, then there exists a continuous homomorphism $S:G_0\rightarrow H$ such that $\ker(S)$ is non-archimedean, where $G_0$ is the connected component of the identity of $G$. The converse holds if $G$ is connected, $S(G)$ is closed in $H$, and the interval $[0,1]$ can be embedded into $H$. As its applications, we prove several Rigid theorems for TSI Lie groups, locally compact Polish groups, separable Banach spaces, and separable Fréchet spaces, respectively.

math.LO↗
arXiv2023

Robust TOA-based Localization with Inaccurate Anchors for MANET

Accurate node localization is vital for mobile ad hoc networks (MANETs). Current methods like Time of Arrival (TOA) can estimate node positions using imprecise baseplates and achieve the Cramér-Rao lower bound (CRLB) accuracy. In multi-hop MANETs, some nodes lack direct links to base anchors, depending on neighbor nodes as dynamic anchors for chain localization. However, the dynamic nature of MANETs challenges TOA's robustness due to the availability and accuracy of base anchors, coupled with ranging errors. To address the issue of cascading positioning error divergence, we first derive the CRLB for any primary node in MANETs as a metric to tackle localization error in cascading scenarios. Second, we propose an advanced two-step TOA method based on CRLB which is able to approximate target node's CRLB with only local neighbor information. Finally, simulation results confirm the robustness of our algorithm, achieving CRLB-level accuracy for small ranging errors and maintaining precision for larger errors compared to existing TOA methods.

cs.NI↗
arXiv2023

Lyapunov-Guided Representation of Recurrent Neural Network Performance

Recurrent Neural Networks (RNN) are ubiquitous computing systems for sequences and multivariate time series data. While several robust architectures of RNN are known, it is unclear how to relate RNN initialization, architecture, and other hyperparameters with accuracy for a given task. In this work, we propose to treat RNN as dynamical systems and to correlate hyperparameters with accuracy through Lyapunov spectral analysis, a methodology specifically designed for nonlinear dynamical systems. To address the fact that RNN features go beyond the existing Lyapunov spectral analysis, we propose to infer relevant features from the Lyapunov spectrum with an Autoencoder and an embedding of its latent representation (AeLLE). Our studies of various RNN architectures show that AeLLE successfully correlates RNN Lyapunov spectrum with accuracy. Furthermore, the latent representation learned by AeLLE is generalizable to novel inputs from the same task and is formed early in the process of RNN training. The latter property allows for the prediction of the accuracy to which RNN would converge when training is complete. We conclude that representation of RNN through Lyapunov spectrum along with AeLLE provides a novel method for organization and interpretation of variants of RNN architectures.

cs.LG↗
arXiv2023

Convex Approximations for a Bi-level Formulation of Data-Enabled Predictive Control

The Willems' fundamental lemma, which characterizes linear time-invariant (LTI) systems using input and output trajectories, has found many successful applications. Combining this with receding horizon control leads to a popular Data-EnablEd Predictive Control (DeePC) scheme. DeePC is first established for LTI systems and has been extended and applied for practical systems beyond LTI settings. However, the relationship between different DeePC variants, involving regularization and dimension reduction, remains unclear. In this paper, we first introduce a new bi-level optimization formulation that combines a data pre-processing step as an inner problem (system identification) and predictive control as an outer problem (online control). We next discuss a series of convex approximations by relaxing some hard constraints in the bi-level optimization as suitable regularization terms, accounting for an implicit identification. These include some existing DeePC variants as well as two new variants, for which we establish their equivalence under appropriate settings. Notably, our analysis reveals a novel variant, called DeePC-SVD-Iter, which has remarkable empirical performance of direct methods on systems beyond deterministic LTI settings.

math.OC↗
arXiv2023

Benign Nonconvex Landscapes in Optimal and Robust Control, Part I: Global Optimality

Direct policy search has achieved great empirical success in reinforcement learning. Many recent studies have revisited its theoretical foundation for continuous control, which reveals elegant nonconvex geometry in various benchmark problems, especially in fully observable state-feedback cases. This paper considers two fundamental optimal and robust control problems with partial observability: the Linear Quadratic Gaussian (LQG) control with stochastic noises, and $\mathcal{H}_\infty$ robust control with adversarial noises. In the policy space, the former problem is smooth but nonconvex, while the latter one is nonsmooth and nonconvex. We highlight some interesting and surprising ``discontinuity'' of LQG and $\mathcal{H}_\infty$ cost functions around the boundary of their domains. Despite the lack of convexity (and possibly smoothness), our main results show that for a class of non-degenerate policies, all Clarke stationary points are globally optimal and there is no spurious local minimum for both LQG and $\mathcal{H}_\infty$ control. Our proof techniques rely on a new and unified framework of Extended Convex Lifting (ECL), which reconciles the gap between nonconvex policy optimization and convex reformulations. This ECL framework is of independent interest, and we will discuss its details in Part II of this paper.

math.OC↗
arXiv2023

Inferring Hybrid Neural Fluid Fields from Videos

We study recovering fluid density and velocity from sparse multiview videos. Existing neural dynamic reconstruction methods predominantly rely on optical flows; therefore, they cannot accurately estimate the density and uncover the underlying velocity due to the inherent visual ambiguities of fluid velocity, as fluids are often shapeless and lack stable visual features. The challenge is further pronounced by the turbulent nature of fluid flows, which calls for properly designed fluid velocity representations. To address these challenges, we propose hybrid neural fluid fields (HyFluid), a neural approach to jointly infer fluid density and velocity fields. Specifically, to deal with visual ambiguities of fluid velocity, we introduce a set of physics-based losses that enforce inferring a physically plausible velocity field, which is divergence-free and drives the transport of density. To deal with the turbulent nature of fluid velocity, we design a hybrid neural velocity representation that includes a base neural velocity field that captures most irrotational energy and a vortex particle-based velocity that models residual turbulent velocity. We show that our method enables recovering vortical flow details. Our approach opens up possibilities for various learning and reconstruction applications centered around 3D incompressible flow, including fluid re-simulation and editing, future prediction, and neural dynamic scene composition. Project website: https://kovenyu.com/HyFluid/

cs.CV↗
arXiv2023

Privacy-Preserving Data-Enabled Predictive Leading Cruise Control in Mixed Traffic

Data-driven predictive control of connected and automated vehicles (CAVs) has received increasing attention as it can achieve safe and optimal control without relying on explicit dynamical models. However, employing the data-driven strategy involves the collection and sharing of privacy-sensitive vehicle information, which is vulnerable to privacy leakage and might further lead to malicious activities. In this paper, we develop a privacy-preserving data-enabled predictive control scheme for CAVs in a mixed traffic environment, where human-driven vehicles and CAVs coexist. We tackle external eavesdroppers and honest-but-curious central unit eavesdroppers who wiretap the communication channel of the mixed traffic system and intend to infer the CAVs' state and input information. An affine masking-based privacy protection method is designed to conceal the true state and input signals, and an extended form of the data-enabled predictive leading cruise control under different matrix structures is derived to achieve privacy-preserving optimal control for CAVs. Numerical simulations demonstrate that the proposed scheme can protect the privacy of CAVs against attackers without affecting control performance or incurring heavy computations.

eess.SY↗
arXiv2023

On the Optimization Landscape of Dynamic Output Feedback: A Case Study for Linear Quadratic Regulator

The convergence of policy gradient algorithms in reinforcement learning hinges on the optimization landscape of the underlying optimal control problem. Theoretical insights into these algorithms can often be acquired from analyzing those of linear quadratic control. However, most of the existing literature only considers the optimization landscape for static full-state or output feedback policies (controllers). We investigate the more challenging case of dynamic output-feedback policies for linear quadratic regulation (abbreviated as dLQR), which is prevalent in practice but has a rather complicated optimization landscape. We first show how the dLQR cost varies with the coordinate transformation of the dynamic controller and then derive the optimal transformation for a given observable stabilizing controller. At the core of our results is the uniqueness of the stationary point of dLQR when it is observable, which is in a concise form of an observer-based controller with the optimal similarity transformation. These results shed light on designing efficient algorithms for general decision-making problems with partially observed information.

cs.LG↗
arXiv2023

On the Optimization Landscape of Dynamic Output Feedback Linear Quadratic Control

The convergence of policy gradient algorithms hinges on the optimization landscape of the underlying optimal control problem. Theoretical insights into these algorithms can often be acquired from analyzing those of linear quadratic control. However, most of the existing literature only considers the optimization landscape for static full-state or output feedback policies (controllers). We investigate the more challenging case of dynamic output-feedback policies for linear quadratic regulation (abbreviated as dLQR), which is prevalent in practice but has a rather complicated optimization landscape. We first show how the dLQR cost varies with the coordinate transformation of the dynamic controller and then derive the optimal transformation for a given observable stabilizing controller. One of our core results is the uniqueness of the stationary point of dLQR when it is observable, which provides an optimality certificate for solving dynamic controllers using policy gradient methods. Moreover, we establish conditions under which dLQR and linear quadratic Gaussian control are equivalent, thus providing a unified viewpoint of optimal control of both deterministic and stochastic linear systems. These results further shed light on designing policy gradient algorithms for more general decision-making problems with partially observed information.

math.OC↗
arXiv2023

A Multimodal Learning Framework for Comprehensive 3D Mineral Prospectivity Modeling with Jointly Learned Structure-Fluid Relationships

This study presents a novel multimodal fusion model for three-dimensional mineral prospectivity mapping (3D MPM), effectively integrating structural and fluid information through a deep network architecture. Leveraging Convolutional Neural Networks (CNN) and Multilayer Perceptrons (MLP), the model employs canonical correlation analysis (CCA) to align and fuse multimodal features. Rigorous evaluation on the Jiaojia gold deposit dataset demonstrates the model's superior performance in distinguishing ore-bearing instances and predicting mineral prospectivity, outperforming other models in result analyses. Ablation studies further reveal the benefits of joint feature utilization and CCA incorporation. This research not only advances mineral prospectivity modeling but also highlights the pivotal role of data integration and feature alignment for enhanced exploration decision-making.

cs.LG↗
arXiv2023

Dimension Reduction for Efficient Data-Enabled Predictive Control

In this letter, we propose a simple yet effective singular value decomposition (SVD) based strategy to reduce the optimization problem dimension in data-enabled predictive control (DeePC). Specifically, in the case of linear time-invariant systems, the excessive input/output measurements can be rearranged into a smaller data library for the non-parametric representation of system behavior. Based on this observation, we develop an SVD-based strategy to pre-process the offline data that achieves dimension reduction in DeePC. Numerical experiments confirm that the proposed method significantly enhances the computation efficiency without sacrificing the control performance.

eess.SY↗
arXiv2023

Smoothing Mixed Traffic with Robust Data-driven Predictive Control for Connected and Autonomous Vehicles

The recently developed DeeP-LCC (Data-EnablEd Predictive Leading Cruise Control) method has shown promising performance for data-driven predictive control of Connected and Autonomous Vehicles (CAVs) in mixed traffic. However, its simplistic zero assumption of the future velocity errors for the head vehicle may pose safety concerns and limit its performance of smoothing traffic flow. In this paper, we propose a robust DeeP-LCC method to control CAVs in mixed traffic with enhanced safety performance. In particular, we first present a robust formulation that enforces a safety constraint for a range of potential velocity error trajectories, and then estimate all potential velocity errors based on the past data from the head vehicle. We also provide efficient computational approaches to solve the robust optimization for online predictive control. Nonlinear traffic simulations show that our robust DeeP-LCC can provide better traffic efficiency and stronger safety performance while requiring less offline data.

math.OC↗
arXiv2023

Hardening RGB-D Object Recognition Systems against Adversarial Patch Attacks

RGB-D object recognition systems improve their predictive performances by fusing color and depth information, outperforming neural network architectures that rely solely on colors. While RGB-D systems are expected to be more robust to adversarial examples than RGB-only systems, they have also been proven to be highly vulnerable. Their robustness is similar even when the adversarial examples are generated by altering only the original images' colors. Different works highlighted the vulnerability of RGB-D systems; however, there is a lacking of technical explanations for this weakness. Hence, in our work, we bridge this gap by investigating the learned deep representation of RGB-D systems, discovering that color features make the function learned by the network more complex and, thus, more sensitive to small perturbations. To mitigate this problem, we propose a defense based on a detection mechanism that makes RGB-D systems more robust against adversarial examples. We empirically show that this defense improves the performances of RGB-D systems against adversarial examples even when they are computed ad-hoc to circumvent this detection mechanism, and that is also more effective than adversarial training.

cs.CV↗
arXiv2023

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking

We introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks. Our data and code are publicly available at: https://pointodyssey.com

cs.CV↗
arXiv2023

On equivalence relations induced by locally compact abelian Polish groups

Given a Polish group $G$, let $E(G)$ be the right coset equivalence relation $G^ω/c(G)$, where $c(G)$ is the group of all convergent sequences in $G$. The connected component of the identity of a Polish group $G$ is denoted by $G_0$. Let $G,H$ be locally compact abelian Polish groups. If $E(G)\leq_B E(H)$, then there is a continuous homomorphism $S:G_0\rightarrow H_0$ such that $\ker(S)$ is non-archimedean. The converse is also true when $G$ is connected and compact. For $n\in{\mathbb N}^+$, the partially ordered set $P(ω)/\mbox{Fin}$ can be embedded into Borel equivalence relations between $E({\mathbb R}^n)$ and $E({\mathbb T}^n)$.

math.LO↗
arXiv2023

On the Relationship of Optimal State Feedback and Disturbance Response Controllers

This paper studies the relationship between state feedback policies and disturbance response policies for the standard Linear Quadratic Regulator (LQR). For open-loop stable plants, we establish a simple relationship between the optimal state feedback controller $u_t=K_\star x_t$ and the optimal disturbance response controller $u_t=L^{(H)}_{\star;1}w_{t-1}+\cdots+L^{(H)}_{\star;H}w_{t-H}$ with $H$-order. Here $x_t, w_t, u_t$ stands for the state, disturbance, control action of the system, respectively. Our result shows that $L_{\star,1}^{(H)}$ is a good approximation of $K_\star$ and the approximation error $\|K_\star - L_{\star,1}^{(H)}\|$ decays exponentially with $H$. We further extend this result to LQR for open-loop unstable systems, when a pre-stabilizing controller $K_0$ is available.

math.OC↗