arXiv subjects

Zhilu Lai

Publications and source records attributed to Zhilu Lai.

At least 19 recordsLinked to original sources

arXiv2026

A unified framework for equation discovery and dynamic prediction of hysteretic systems

Hysteresis is a nonlinear phenomenon with memory effects, where a system's output depends on both its current state and past states. It is prevalent in various physical and mechanical systems, such as yielding structures under seismic excitation, ferromagnetic materials, and piezoelectric actuators. Analytical models like the Bouc-Wen model are often employed but rely on idealized assumptions and careful parameter calibration, limiting their applicability to diverse or mechanism-unknown behaviors. Existing equation discovery approaches for hysteresis are often system-specific or rely on predefined model libraries, which limit their flexibility and ability to capture the hidden mechanisms. To address these challenges, this research classifies equation discovery problems for hysteretic systems and develops a unified framework in which the state-space form is reformulated, and hysteretic variables are treated as trainable parameters from data. The framework further employs symbolic regression (SR) to automatically recover explicit governing equations without relying on predefined libraries, unlike methods such as sparse identification of nonlinear dynamics (SINDy). Experimental results demonstrate that the proposed method is effective in recovering governing equations for hysteretic systems, even in a challenging Full Equation Discovery setting, where prior information is extremely limited, and solving the equations naturally enables the dynamic prediction of hysteretic systems.

cs.CE↗

arXiv2026

On the Rate of Convergence of Kolmogorov-Arnold Network Regression Estimators

Kolmogorov-Arnold Networks (KANs) approximate multivariate functions by composing univariate transformations through additive or multiplicative aggregation. We establish convergence guarantees for KANs whose univariate components are B-splines. The least-squares estimator over the KAN spline sieve attains the rate $O((\log n / n)^{2r/(2r+1)})$, uniformly over a ball of regression functions admitting a KAN representation with univariate components of Sobolev smoothness $r$; a matching lower bound of order $n^{-2r/(2r+1)}$ shows this is minimax optimal up to the logarithmic factor, which we trace to the nonlinearity of the sieve rather than to the architecture. The rate is free of the ambient dimension $d$; this dimension-free exponent reflects the assumed KAN structure of the target, not an escape from the minimax rate $n^{-2r/(2r+d)}$ on Sobolev classes over $[0,1]^d$. We derive a knot-selection rule, show that penalized selection over a dyadic knot grid attains the rate adaptively in the unknown smoothness, and show that univariate components are not identifiable under centering alone, so consistency of the fit does not imply consistency of the components. On targets of exactly known smoothness the fitted risk exponent is at least as steep as the bound in every configuration, and the predicted knot scaling and $k^{-r}$ approximation decay are checked directly.

cs.LG↗

arXiv2026

LMMSE-Optimal Pilot Pattern Design Based on Covariance Matrix Approximation for OFDM Channel Estimation in Doubly Dispersive Channel

This paper investigates the optimal pilot pattern design, in the linear minimum mean square error (LMMSE) estimator sense, for OFDM systems in doubly dispersive channels. To enable analytical tractability, the channel covariance matrix is decomposed into the Kronecker product of two Hermitian Toeplitz matrices corresponding to the delay and Doppler domains. By invoking the Szegö limit theorem, these matrices are shown to be approximately diagonalizable by discrete Fourier transform (DFT) matrices. Based on this structure, the LMMSE channel estimation error is reformulated into a compact analytical form, from which a closed-form lower bound is derived. Furthermore, we establish the condition under which this bound is achieved by a lattice-based pilot pattern. Numerical results verify that the proposed matrix approximation introduces negligible error and examples of the proposed lattice design are given.

eess.SP↗

arXiv2026

Reformulating Neural Operators in $d+1$ Dimensions for Embedding Evolution

Neural Operators (NOs) are powerful architectures for learning mappings between function spaces. While most advances focus on refining kernel parameterizations over the $d$-dimensional physical domain, the evolution of lifted embeddings remains underexplored, which often drives models toward computationally expensive embedding-scaling designs to improve approximation. In this paper, we introduce an auxiliary function dimension that models embedding evolution in operator form, thereby reformulating the NO pipeline in $d+1$ dimensions. We instantiate this framework via Fourier-based operators acting jointly on the physical and auxiliary domains, yielding a basis-diversified auxiliary evolution module as an alternative to brute-force embedding scaling. Across more than ten increasingly challenging benchmarks, ranging from the 1D heat equation to the highly nonlinear 3D Rayleigh-Taylor instability, our model consistently achieves the lowest relative $L_2$ error among the evaluated baselines. Crucially, this advantage is empirically supported by (1) controlled budget-aware comparisons against scaled and ablated baselines; (2) robustness under mixed-resolution training and super-resolution inference; and (3) zero-shot generalization to unseen temporal regimes. In addition, we present a broader set of design choices for lifting and recovery operators, demonstrating their impact on our model's predictive performance.

cs.LG↗

arXiv2026

Reconstructing Multi-Scale Physical Fields from Extremely Sparse Measurements with an Autoencoder-Diffusion Cascade

Extreme sensor sparsity makes full-field reconstruction a fundamentally ill-posed problem in scientific sensing,where the goal is to infer physical fields from sparse measurements.In this regime,the posterior is severely underconstrained and inherently multimodal,making its approximation highly ill-conditioned.Specifically,deterministic mappings collapse uncertainty,direct conditional learning cannot cover the space of possible observation-conditioned solutions,and likelihood-guided sampling becomes highly sensitive to noise and sensor configurations.These limitations result in unstable posterior estimates and highlight the need for modeling uncertainty in a structural manner.To this end,we propose Cascaded Sensing,a hierarchical framework that restructures posterior inference across scales.Rather than modeling the full-field posterior directly,Cas-Sensing first resolves global structural ambiguity through a deterministic coarse-stage estimator.A neural-operator-based functional autoencoder,trained with masked inputs,maps sparse observations to a coarse-scale structural field,acting analogously to a maximum a posteriori estimator that selects the dominant global configuration.This structural anchor fixes the principal degrees of freedom of the posterior and transforms the problem into a better-conditioned residual inference task.A conditional diffusion model then learns only the refined-scale residual distribution,confining sampling to a stable neighborhood of plausible solutions and suppressing competition among observation-consistent modes.To enhance robustness under varying sensing conditions,we introduce mask-cascade training,which exposes the model to diverse sparse observation patterns through intermediate coarse reconstructions.During inference,manifold-constrained guidance enforces observation consistency as a refinement mechanism rather than a global mode-selection process.

cs.LG↗

arXiv2026

Optimal Pilot Pattern Design for LMMSE Channel Estimation in OFDM Systems with Finite Block Size over Doubly Dispersive Channels

Pilot pattern design over doubly dispersive channels has regained significant research interest, driven by emerging high-mobility applications in 5G-Advanced and 6G systems, as well as recent developments in Orthogonal Time Frequency Space (OTFS) modulation. This paper addresses the design of LMMSE-optimal pilot patterns for OFDM systems over doubly dispersive channels with finite time-frequency grids. We formulate the problem as A-optimal sensor selection and propose two heuristic algorithms, both combining an initialization stage with local swap refinement. The first employs convex relaxation with randomized rounding, while the second uses greedy selection. Simulations on practical resource block dimensions demonstrate that the proposed designs consistently outperform conventional rectangular and diamond lattice patterns.

eess.SP↗

arXiv2026

From Basis to Basis: Gaussian Particle Representation for Interpretable PDE Operators

Learning PDE dynamics for fluids increasingly relies on neural operators and Transformer-based models, yet these approaches often lack interpretability and struggle with localized, high-frequency structures while incurring quadratic cost in spatial samples. We propose representing fields with a Gaussian basis, where learned atoms carry explicit geometry (centers, anisotropic scales, weights) and form a compact, mesh-agnostic, directly visualizable state. Building on this representation, we introduce a Gaussian Particle Operator that acts in modal space: learned Gaussian modal windows perform a Petrov-Galerkin measurement, and PG Gaussian Attention enables global cross-scale coupling. This basis-to-basis design is resolution-agnostic and achieves near-linear complexity in N for a fixed modal budget, supporting irregular geometries and seamless 2D-to-3D extension. On standard PDE benchmarks and real datasets, our method attains state-of-the-art competitive accuracy while providing intrinsic interpretability.

cs.LG↗

arXiv2026

Physics-Consistent Diffusion for Efficient Fluid Super-Resolution via Multiscale Residual Correction

Existing image SR and generic diffusion models transfer poorly to fluid SR: they are sampling-intensive, ignore physical constraints, and often yield spectral mismatch and spurious divergence. We address fluid super-resolution (SR) with \textbf{ReMD} (\underline{Re}sidual-\underline{M}ultigrid \underline{D}iffusion), a physics-consistent diffusion framework. At each reverse step, ReMD performs a \emph{multigrid residual correction}: the update direction is obtained by coupling data consistency with lightweight physics cues and then correcting the residual across scales; the multiscale hierarchy is instantiated with a \emph{multi-wavelet} basis to capture both large structures and fine vortical details. This coarse-to-fine design accelerates convergence and preserves fine structures while remaining equation-free. Across atmospheric and oceanic benchmarks, ReMD improves accuracy and spectral fidelity, reduces divergence, and reaches comparable quality with markedly fewer sampling steps than diffusion baselines. Our results show that enforcing physics consistency \emph{inside} the diffusion process via multigrid residual correction and multi-wavelet multiscale modeling is an effective route to efficient fluid SR. Our code are available on https://github.com/lizhihao2022/ReMD.

cs.CV↗

arXiv2026

Structure-Aware Epistemic Uncertainty Quantification for Neural Operator PDE Surrogates

Neural operators (NOs) provide fast, resolution-invariant surrogates for mapping input fields to PDE solution fields, but their predictions can exhibit significant epistemic uncertainty due to finite data, imperfect optimization, and distribution shift. For practical deployment in scientific computing, uncertainty quantification (UQ) must be both computationally efficient and spatially faithful, i.e., uncertainty bands should align with the localized residual structures that matter for downstream risk management. We propose a structure-aware epistemic UQ scheme that exploits the modular anatomy common to modern NOs (lifting-propagation-recovering). Instead of applying unstructured weight perturbations (e.g., naive dropout) across the entire network, we restrict Monte Carlo sampling to a module-aligned subspace by injecting stochasticity only into the lifting module, and treat the learned solver dynamics (propagation and recovery) as deterministic. We instantiate this principle with two lightweight lifting-level perturbations, including channel-wise multiplicative feature dropout and a Gaussian feature perturbation with matched variance, followed by standard calibration to construct uncertainty bands. Experiments on challenging PDE benchmarks (including discontinuous-coefficient Darcy flow and geometry-shifted 3D car CFD surrogates) demonstrate that the proposed structure-aware design yields more reliable coverage, tighter bands, and improved residual-uncertainty alignment compared with common baselines, while remaining practical in runtime.

cs.LG↗

arXiv2025

M2NO: An Efficient Multi-Resolution Operator Framework for Dynamic Multi-Scale PDE Solvers

Solving high-dimensional partial differential equations (PDEs) efficiently requires handling multi-scale features across varying resolutions. To address this challenge, we present the Multiwavelet-based Multigrid Neural Operator (M2NO), a deep learning framework that integrates a multigrid structure with predefined multiwavelet spaces. M2NO leverages multi-resolution analysis to selectively transfer low-frequency error components to coarser grids while preserving high-frequency details at finer levels. This design enhances both accuracy and computational efficiency without introducing additional complexity. Moreover, M2NO serves as an effective preconditioner for iterative solvers, further accelerating convergence in large-scale PDE simulations. Through extensive evaluations on diverse PDE benchmarks, including high-resolution, super-resolution tasks, and preconditioning settings, M2NO consistently outperforms existing models. Its ability to efficiently capture fine-scale variations and large-scale structures makes it a robust and versatile solution for complex PDE simulations. Our code and datasets are available on https://github.com/lizhihao2022/M2NO.

cs.LG↗

arXiv2025

Characterizing ISCI in Multi-carrier ISAC Systems over Doubly Dispersive Channel: Joint Sensing and Communication Performance Analysis

This paper presents a systematic analysis of inter-symbol and inter-carrier interference (ISCI) modeling in doubly dispersive channels for integrated sensing and communication (ISAC) systems. We propose a generalized OFDM (Weyl-Heisenberg) framework to evaluate four ISCI treatment approaches: (1) explicit estimation and compensation, (2) complete ignorance, (3) uncorrelated colored noise approximation, and (4) correlated colored noise modeling. Through continuous delay-Doppler channel characterization, we derive LMMSE channel estimators and corresponding estimation errors (as sensing metrics) for both pilot-assisted and fully-known symbol scenarios. The communication performance is quantified via ergodic capacity bounds under imperfect CSI. Our theoretical analysis and numerical results reveal fundamental performance-complexity trade-offs, providing insights for practical ISAC waveform and receiver design in doubly dispersive channels.

eess.SP↗

arXiv2025

KP-PINNs: Kernel Packet Accelerated Physics Informed Neural Networks

Differential equations are involved in modeling many engineering problems. Many efforts have been devoted to solving differential equations. Due to the flexibility of neural networks, Physics Informed Neural Networks (PINNs) have recently been proposed to solve complex differential equations and have demonstrated superior performance in many applications. While the L2 loss function is usually a default choice in PINNs, it has been shown that the corresponding numerical solution is incorrect and unstable for some complex equations. In this work, we propose a new PINNs framework named Kernel Packet accelerated PINNs (KP-PINNs), which gives a new expression of the loss function using the reproducing kernel Hilbert space (RKHS) norm and uses the Kernel Packet (KP) method to accelerate the computation. Theoretical results show that KP-PINNs can be stable across various differential equations. Numerical experiments illustrate that KP-PINNs can solve differential equations effectively and efficiently. This framework provides a promising direction for improving the stability and accuracy of PINNs-based solvers in scientific computing.

cs.CE↗

arXiv2025

Mechanical in-sensor computing: a programmable meta-sensor for structural damage classification without external electronic power

Structural health monitoring (SHM) involves sensor deployment, data acquisition, and data interpretation, commonly implemented via a tedious wired system. The information processing in current practice majorly depends on electronic computers, albeit with universal applications, delivering challenges such as high energy consumption and low throughput due to the nature of digital units. In recent years, there has been a renaissance interest in shifting computations from electronic computing units to the use of real physical systems, a concept known as physical computation. This approach provides the possibility of thinking out of the box for SHM, seamlessly integrating sensing and computing into a pure-physical entity, without relying on external electronic power supplies, thereby properly coping with resource-restricted scenarios. The latest advances of metamaterials (MM) hold great promise for this proactive idea. In this paper, we introduce a programmable metamaterial-based sensor (termed as MM-sensor) for physically processing structural vibration information to perform specific SHM tasks, such as structural damage warning (binary classification) in this initiation, without the need for further information processing or resource-consuming, that is, the data collection and analysis are completed in-situ at the sensor level. We adopt the configuration of a locally resonant metamaterial plate (LRMP) to achieve the first fabrication of the MM-sensor. We take advantage of the bandgap properties of LRMP to physically differentiate the dynamic behavior of structures before and after damage. By inversely designing the geometric parameters, our current approach allows for adjustments to the bandgap features. This is effective for engineering systems with a first natural frequency ranging from 9.54 Hz to 81.86 Hz.

cs.LG↗

arXiv2025

Transforming physics-informed machine learning to convex optimization

Physics-Informed Machine Learning (PIML) offers a powerful paradigm of integrating data with physical laws to address important scientific problems, such as parameter estimation, inferring hidden physics, equation discovery, and state prediction, etc. However, PIML still faces many serious optimization challenges that significantly restrict its applications. In this study, we propose a comprehensive framework that transforms PIML to convex optimization to overcome all these limitations, referred to as Convex-PIML. The linear combination of B-splines is utilized to approximate the data, promoting the convexity of the loss function. By replacing the non-convex components of the loss function with convex approximations, the problem is further converted into a sequence of successively refined approximated convex optimization problems. This conversion allows the use of well-established convex optimization algorithms, obtaining solutions effectively and efficiently. Furthermore, an adaptive knot optimization method based on error estimate is introduced to mitigate the spectral bias issue of PIML, further improving the performance. The proposed theoretically guaranteed framework is tested in scenarios with distinct types of physical prior. The results indicate that optimization problems are effectively solved in these scenarios, highlighting the potential of the framework for broad applications.

cs.CE↗

arXiv2025

Parameter estimation of structural dynamics with neural operators enabled surrogate modeling

Parameter estimation in structural dynamics generally involves inferring the values of physical, geometric, or even customized parameters based on first principles or expert knowledge, which is challenging for complex structural systems. In this work, we present a unified deep learning-based framework for parameterization, forward modeling, and inverse modeling of structural dynamics. The parameterization is flexible and can be user-defined, including physical and/or non-physical (customized) parameters. In the forward modeling, we train a neural operator for response prediction -- forming a surrogate model, which leverages the defined system parameters and excitation forces as inputs to the model. The inverse modeling focuses on estimating system parameters. In particular, the learned forward surrogate model (which is differentiable) is utilized for preliminary parameter estimation via gradient-based optimization; to further boost the parameter estimation, we introduce a neural refinement method to mitigate ill-posed problems, which often occur in the former. The framework's effectiveness is verified numerically and experimentally, in both interpolation and extrapolation cases, indicating its capability to capture intrinsic dynamics of structural systems from both forward and inverse perspectives. Moreover, the framework's flexibility is expected to support a wide range of applications, including surrogate modeling, structural identification, damage detection, and inverse design of structural systems.

cs.CE↗

arXiv2025

Neural Preconditioning Operator for Efficient PDE Solves

We introduce the Neural Preconditioning Operator (NPO), a novel approach designed to accelerate Krylov solvers in solving large, sparse linear systems derived from partial differential equations (PDEs). Unlike classical preconditioners that often require extensive tuning and struggle to generalize across different meshes or parameters, NPO employs neural operators trained via condition and residual losses. This framework seamlessly integrates with existing neural network models, serving effectively as a preconditioner to enhance the performance of Krylov subspace methods. Further, by melding algebraic multigrid principles with a transformer-based architecture, NPO significantly reduces iteration counts and runtime for solving Poisson, Diffusion, and Linear Elasticity problems on both uniform and irregular meshes. Our extensive numerical experiments demonstrate that NPO outperforms traditional methods and contemporary neural approaches across various resolutions, ensuring robust convergence even on grids as large as 4096, far exceeding its initial training limits. These findings underscore the potential of data-driven preconditioning to transform the computational efficiency of high-dimensional PDE applications.

cs.CE↗

arXiv2025

Harnessing Scale and Physics: A Multi-Graph Neural Operator Framework for PDEs on Arbitrary Geometries

Partial Differential Equations (PDEs) underpin many scientific phenomena, yet traditional computational approaches often struggle with complex, nonlinear systems and irregular geometries. This paper introduces the AMG method, a Multi-Graph neural operator approach designed for efficiently solving PDEs on Arbitrary geometries. AMG leverages advanced graph-based techniques and dynamic attention mechanisms within a novel GraphFormer architecture, enabling precise management of diverse spatial domains and complex data interdependencies. By constructing multi-scale graphs to handle variable feature frequencies and a physics graph to encapsulate inherent physical properties, AMG significantly outperforms previous methods, which are typically limited to uniform grids. We present a comprehensive evaluation of AMG across six benchmarks, demonstrating its consistent superiority over existing state-of-the-art models. Our findings highlight the transformative potential of tailored graph neural operators in surmounting the challenges faced by conventional PDE solvers. Our code and datasets are available on https://github.com/lizhihao2022/AMG.

cs.LG↗

arXiv2024

Transferring self-supervised pre-trained models for SHM data anomaly detection with scarce labeled data

Structural health monitoring (SHM) has experienced significant advancements in recent decades, accumulating massive monitoring data. Data anomalies inevitably exist in monitoring data, posing significant challenges to their effective utilization. Recently, deep learning has emerged as an efficient and effective approach for anomaly detection in bridge SHM. Despite its progress, many deep learning models require large amounts of labeled data for training. The process of labeling data, however, is labor-intensive, time-consuming, and often impractical for large-scale SHM datasets. To address these challenges, this work explores the use of self-supervised learning (SSL), an emerging paradigm that combines unsupervised pre-training and supervised fine-tuning. The SSL-based framework aims to learn from only a very small quantity of labeled data by fine-tuning, while making the best use of the vast amount of unlabeled SHM data by pre-training. Mainstream SSL methods are compared and validated on the SHM data of two in-service bridges. Comparative analysis demonstrates that SSL techniques boost data anomaly detection performance, achieving increased F1 scores compared to conventional supervised training, especially given a very limited amount of labeled data. This work manifests the effectiveness and superiority of SSL techniques on large-scale SHM data, providing an efficient tool for preliminary anomaly detection with scarce label information.

cs.LG↗