arXiv subjects

Heling Zhang

Publications and source records attributed to Heling Zhang.

13 recordsLinked to original sources

arXiv2026

Formalizing Task-Space Complexity for Zero-Shot Generalization

Policies must operate across diverse conditions, yet a single policy is often conservative while fully adaptive schemes can be complex. We study zero-shot generalization in contextual dynamical systems and introduce a performance-centric, directional task dissimilarity--the signed divergence--that upper bounds the generalization gap from a source context to a target context. The signed divergence induces $\varepsilon$-tolerance sets that certify when a source policy class generalizes, and it yields a concrete notion of task-space complexity: the minimum number of source contexts needed so that every target context incurs at most $\varepsilon$ generalization gap. Under a mild local smoothness assumption on performance, the induced tolerance sets admit certified inner/outer balls and instance-dependent volume bounds on task-space complexity. In the finite-oracle setting, source selection reduces to set cover; a greedy strategy inherits the standard $H(n)$ approximation guarantee. Using a Mass-Spring-Damper system with linear-quadratic regulator (LQR) controllers and a nonlinear CartPole system with deep reinforcement learning controllers, we show that greedy selection achieves the same $\varepsilon$-coverage with fewer policies than uniform or random baselines. Our approach delivers a performance-based task similarity measure and practical certificates for building generalizable control with simple policies.

cs.LG↗

arXiv2026

Beyond Spherical Wavefront: Near-Field Channel Estimation Under Wavefront Anisotropy

Extremely large aperture arrays (ELAAs) and millimeter-wave (mmWave) technologies are essential for achieving high data rates in future wireless communication systems. To perform precise beamforming, these systems require accurate channel estimation, in which the near-field wavefront curvature effect must be taken into account. Existing channel estimation methods rely on the spherical wavefront channel (SWC) model, which is suitable for near-field propagation with point sources, scatterers, and reflection planes. However, when a near-field curved reflecting surface exists, the wavefront of the reflected wave becomes anisotropic rather than spherical, causing the SWC model to become inaccurate. To address this problem, in this paper, we formulate a parameterized model for the anisotropic wavefront channel (AWC). Using this model, we propose a channel estimation algorithm based on physical parameter recovery for the AWC. Simulation results reveal that the AWC no longer retains sparsity in the angle-distance domain. Furthermore, the results demonstrate how different physical characteristics of the propagation scenario affect the degree of wavefront anisotropy, and confirm the effectiveness of our proposed algorithm in AWC scenarios.

eess.SP↗

arXiv2026

Matching-free Acquisition of Channels with Anisotropic Wavefronts

The escalating data rate demands of future wireless communications necessitate the deployment of extremely large aperture arrays (ELAAs) in communication systems. Acquiring accurate channel state information is crucial to execute effective precoding for such systems, in which the near-field curvature effects on the channel must be considered. Current channel estimation algorithms are generally restricted to the spherical wavefront channel (SWC), which is appropriate for isotropic scatterers, point sources, and planar reflecting surfaces. However, in practical scenarios involving curved reflecting surfaces, the reflected waves exhibit anisotropic rather than spherical wavefronts, significantly degrading the accuracy of conventional SWC-based algorithms. To tackle this challenge, we first derive a parameterized model for the anisotropic wavefront channel (AWC). Based on this model, we then propose the matching-free acquisition of channels with anisotropic wavefronts (MACAW) algorithm. Unlike conventional dictionary-based matching pursuit techniques, MACAW recovers channel parameters through fast-Fourier-transform-based frequency analysis. This approach enables precise channel estimation in AWC scenarios while maintaining a significantly lower computational complexity than existing methods. Simulation results illustrate how physical characteristics of the propagation environment influence the degree of wavefront anisotropy, and demonstrate the effectiveness of the proposed algorithm.

eess.SP↗

arXiv2026

A Controllability Perspective on Steering Follow-the-Regularized-Leader Learners in Games

Follow-the-regularized-leader (FTRL) algorithms have become popular in the context of games, providing easy-to-implement methods for each agent, as well as theoretical guarantees that the strategies of all agents will converge to some equilibrium concept (provided that all agents follow the appropriate dynamics). However, with these methods, each agent ignores the coupling in the game, and treats their payoff vectors as exogenously given. In this paper, we take the perspective of one agent (the controller) deciding their mixed strategies in a finite game, while one or more other agents update their mixed strategies according to continuous-time FTRL. Viewing the learners' dynamics as a nonlinear control system evolving on the relative interior of a simplex or product of simplices, we ask when the controller can steer the learners to a target state, using only its own mixed strategy and without modifying the game's payoff structure. For the two-player case we provide a necessary and sufficient criterion for controllability based on the existence of a fully mixed neutralizing controller strategy and a rank condition on the projected payoff map. For multi-learner interactions we give two sufficient controllability conditions, one based on uniform neutralization and one based on a periodic-drift hypothesis together with a Lie-algebra rank condition. We illustrate these results on canonical examples such as Rock-Paper-Scissors and a construction related to Brockett's integrator.

eess.SY↗

arXiv2026

Constructing Knowledge Map for MIMO-OFDM Clustered Channel Estimation

Channel knowledge map (CKM) exploits environ-ment information to assist channel estimation during communi-cation. For clustered channels, which represent a typical type ofwireless propagation environment, there has been no researchdevoted to designing an appropriate CKM to enhance theirestimation. To exploit environment information for clusteredchannel, improve channel estimation accuracy and reduce pilotoverhead, we propose ClusterCKM, a CKM providing the rangeof clustered multipath parameters for any pair of transmitter-receiver links in the region of interest. Firstly, we construct Clus-terCKM through estimating the spatial range of scatterer clustersfrom historical channel information. From these spatial range ofscatterer clusters, ClusterCKM infers the range of multipathparameters for the target link. Furthermore, a ClusterCKM-based channel estimation algorithm is developed to utilize theparameter range provided by ClusterCKM. Simulation resultsshow that, more accurate channel estimation can be achievedand pilot overhead can also be reduced by ClusterCKM and theClusterCKM-based estimation algorithm.

eess.SP↗

arXiv2025

Interaction-aware Conformal Prediction for Crowd Navigation

During crowd navigation, robot motion plan needs to consider human motion uncertainty, and the human motion uncertainty is dependent on the robot motion plan. We introduce Interaction-aware Conformal Prediction (ICP) to alternate uncertainty-aware robot motion planning and decision-dependent human motion uncertainty quantification. ICP is composed of a trajectory predictor to predict human trajectories, a model predictive controller to plan robot motion with confidence interval radii added for probabilistic safety, a human simulator to collect human trajectory calibration dataset conditioned on the planned robot motion, and a conformal prediction module to quantify trajectory prediction error on the decision-dependent calibration dataset. Crowd navigation simulation experiments show that ICP strikes a good balance of performance among navigation efficiency, social awareness, and uncertainty quantification compared to previous works. ICP generalizes well to navigation tasks under various crowd densities. The fast runtime and efficient memory usage make ICP practical for real-world applications. Code is available at https://github.com/tedhuang96/icp.

cs.RO↗

arXiv2024

Channel Correlation Matrix Extrapolation Based on Roughness Calibration of Scatterers

To estimate the channel correlation matrix (CCM) in areas where channel information cannot be collected in advance, this paper proposes a way to spatially extrapolate CCM based on the calibration of the surface roughness parameters of scatterers in the propagation scene. We calibrate the roughness parameters of scene scatters based on CCM data in some specific areas. From these calibrated roughness parameters, we are able to generate a good prediction of the CCM for any other area in the scene by performing ray tracing. Simulation results show that the channel extrapolation method proposed in this paper can effectively realize the extrapolation of the CCM between different areas in frequency domain, or even from one domain to another.

eess.SP↗

arXiv2024

Distribution-Free Guarantees for Systems with Decision-Dependent Noise

In many real-world dynamical systems, obtaining precise models of system uncertainty remains a challenge. It may be difficult to estimate noise distributions or robustness bounds, especially when the distributions/robustness bounds vary with different control inputs in unknown ways. Addressing this challenge, this paper presents a novel iterative method tailored for systems with decision-dependent noise without prior knowledge of the distributions. Our approach finds the open-loop control law that minimizes the worst-case loss, given that the noise induced by this control lies in its $(1 - p)$-confidence set for a predetermined $p$. At each iteration, we use a quantile method inspired by conformal prediction to empirically estimate the confidence set shaped by the preceding control law. These derived confidence sets offer distribution-free guarantees on the system's noise, guiding a robust control formulation that targets worst-case loss minimization. Under specific regularity conditions, our method is shown to converge to a near-optimal open-loop control. While our focus is on open-loop controls, the adaptive, data-driven nature of our approach suggests its potential applicability across diverse scenarios and extensions.

eess.SY↗

arXiv2023

Unlocking the Potential of Deep Learning in Peak-Hour Series Forecasting

Unlocking the potential of deep learning in Peak-Hour Series Forecasting (PHSF) remains a critical yet underexplored task in various domains. While state-of-the-art deep learning models excel in regular Time Series Forecasting (TSF), they struggle to achieve comparable results in PHSF. This can be attributed to the challenges posed by the high degree of non-stationarity in peak-hour series, which makes direct forecasting more difficult than standard TSF. Additionally, manually extracting the maximum value from regular forecasting results leads to suboptimal performance due to models minimizing the mean deficit. To address these issues, this paper presents Seq2Peak, a novel framework designed specifically for PHSF tasks, bridging the performance gap observed in TSF models. Seq2Peak offers two key components: the CyclicNorm pipeline to mitigate the non-stationarity issue and a simple yet effective trainable-parameter-free peak-hour decoder with a hybrid loss function that utilizes both the original series and peak-hour series as supervised signals. Extensive experimentation on publicly available time series datasets demonstrates the effectiveness of the proposed framework, yielding a remarkable average relative improvement of 37.7% across four real-world datasets for both transformer- and non-transformer-based TSF models.

cs.LG↗

arXiv2021

Approximate Regions of Attraction in Learning with Decision-Dependent Distributions

As data-driven methods are deployed in real-world settings, the processes that generate the observed data will often react to the decisions of the learner. For example, a data source may have some incentive for the algorithm to provide a particular label (e.g. approve a bank loan), and manipulate their features accordingly. Work in strategic classification and decision-dependent distributions seeks to characterize the closed-loop behavior of deploying learning algorithms by explicitly considering the effect of the classifier on the underlying data distribution. More recently, works in performative prediction seek to classify the closed-loop behavior by considering general properties of the mapping from classifier to data distribution, rather than an explicit form. Building on this notion, we analyze repeated risk minimization as the perturbed trajectories of the gradient flows of performative risk minimization. We consider the case where there may be multiple local minimizers of performative risk, motivated by situations where the initial conditions may have significant impact on the long-term behavior of the system. We provide sufficient conditions to characterize the region of attraction for the various equilibria in this settings. Additionally, we introduce the notion of performative alignment, which provides a geometric condition on the convergence of repeated risk minimization to performative risk minimizers.

cs.LG↗

arXiv2021

BiTe-GCN: A New GCN Architecture via BidirectionalConvolution of Topology and Features on Text-Rich Networks

Graph convolutional networks (GCNs), aiming to integrate high-order neighborhood information through stacked graph convolution layers, have demonstrated remarkable power in many network analysis tasks. However, topological limitations, including over-smoothing and local topology homophily, limit its capability to represent networks. Existing studies only perform feature convolution on network topology, which inevitably introduces unbalance between topology and features. Considering that in real world, the information network consists of not only the node-level citation information but also the local text-sequence information. We propose BiTe-GCN, a novel GCN architecture with bidirectional convolution of both topology and features on text-rich networks to solve these limitations. We first transform the original text-rich network into an augmented bi-typed heterogeneous network, capturing both the global node-level information and the local text-sequence information from texts. We then introduce discriminative convolution mechanisms to performs convolutions of both topology and features simultaneously. Extensive experiments on text-rich networks demonstrate that our new architecture outperforms state-of-the-art by a breakout improvement. Moreover, this architecture can also be applied to several e-commerce searching scenes such as JD searching. The experiments on the JD dataset validate the superiority of the proposed architecture over the related methods.

cs.LG↗

arXiv2021

The Twelvefold Way of Non-Sequential Lossless Compression

Many information sources are not just sequences of distinguishable symbols but rather have invariances governed by alternative counting paradigms such as permutations, combinations, and partitions. We consider an entire classification of these invariances called the twelvefold way in enumerative combinatorics and develop a method to characterize lossless compression limits. Explicit computations for all twelve settings are carried out for i.i.d. uniform and Bernoulli distributions. Comparisons among settings provide quantitative insight.

cs.IT↗

arXiv2018

Learning to Communicate: A Machine Learning Framework for Heterogeneous Multi-Agent Robotic Systems

We present a machine learning framework for multi-agent systems to learn both the optimal policy for maximizing the rewards and the encoding of the high dimensional visual observation. The encoding is useful for sharing local visual observations with other agents under communication resource constraints. The actor-encoder encodes the raw images and chooses an action based on local observations and messages sent by the other agents. The machine learning agent generates not only an actuator command to the physical device, but also a communication message to the other agents. We formulate a reinforcement learning problem, which extends the action space to consider the communication action as well. The feasibility of the reinforcement learning framework is demonstrated using a 3D simulation environment with two collaborating agents. The environment provides realistic visual observations to be used and shared between the two agents.

cs.RO↗