arXiv subjects

Haizhao Yang

Publications and source records attributed to Haizhao Yang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Sobolev Approximation by Fixed-Size Neural Networks with Arbitrary Accuracy

In this work, we investigate new activation functions for achieving arbitrary-accuracy Sobolev approximation by fixed-size neural networks. We first show that any function in $W^{2,\infty}((a,b)^d)$ can be approximated with arbitrary accuracy, measured in the $W^{1,\infty}$-norm, by a fixed-size neural network using the Elementary Universal Activation Function ($\mathrm{EUAF}$). To extend this result to $W^{s,\infty}((a,b)^d)$ for $s\in\mathbb{N}$, we introduce a smooth activation $\mathrm{DUAF}_{\infty}$ from the family of Differentiable Universal Activation Functions ($\mathrm{DUAF}_n$). We prove that any function in $W^{s,\infty}((a,b)^d)$ can be approximated with arbitrary accuracy in the $W^{s-1,\infty}$-norm by a fixed-size $\mathrm{DUAF}_{\infty}$-activated network. We further construct sigmoidal variants $\widetilde{\mathrm{DUAF}}_n$ and show that, for every $1\leq s\leq n$, fixed-size $\widetilde{\mathrm{DUAF}}_n$-activated networks still approximate any $f\in W^{s,\infty}((a,b)^d)$ with arbitrary accuracy in the $W^{s-1,\infty}$-norm. In all these results, the width and depth bounds are computed explicitly, and the proposed activations are elementary.

stat.ML↗

arXiv2026

Geometry-Aware Hallucination Detection in Large Language Models

Large language models (LLMs) frequently generate factually incorrect or unsupported content, commonly referred to as hallucinations. Prior work has explored decoding strategies, retrieval augmentation, and supervised fine-tuning for hallucination detection, while recent studies show that in-context learning (ICL) can substantially influence factual reliability. However, existing ICL demonstration selection methods often rely on surface-level similarity heuristics and exhibit limited robustness across tasks and models. We propose GA-ICL, a geometry-aware demonstration sampling framework for selecting in-context demonstrations that leverages latent representations extracted from frozen LLMs. By jointly modeling local manifold structure and class-aware prototype geometry, GA-ICL selects demonstrations based on their proximity to learned prototypes rather than lexical or embedding similarity alone. Across factual verification (FEVER) and hallucination detection (HaluEval) benchmarks, GA-ICL outperforms standard ICL selection baselines in the majority of evaluated settings, with particularly strong gains on dialogue and summarization tasks. The method remains robust under temperature perturbations and model variation, indicating improved stability compared to heuristic retrieval strategies. While lexical retrieval can remain competitive in certain question-answering regimes at smaller model scales, our results demonstrate that geometry-aware prototype selection provides a reliable and training-light approach for hallucination detection without modifying LLM parameters. Extended evaluations on Phi-14B and Qwen3-32B confirm that GA-ICL scales effectively to larger models, outperforming all compared baselines including on QA tasks where smaller models show boundary-condition limitations, offering a principled direction for improved ICL demonstration selection.

cs.LG↗

arXiv2026

Global Convergence and Error Propagation in Neural Gradient Flows: A Riemannian Optimization Framework

We develop a geometric convergence theory for neural-network optimization within the minimizing movement scheme (MMS) framework. Reformulating each neural MMS step as a minimization over the set of increments in a Hilbert space, we show that under a $C^2$ network with locally non-degenerate Jacobian this increment set is a boundaryless smooth embedded submanifold, on which a natural preconditioned (Gauss--Newton-type) gradient flow in parameter space induces exactly the Riemannian gradient flow. Under a strict interior-localization condition and an explicit data condition, the reached sublevel set is geodesically convex and the subproblem objective is geodesically strongly convex on it; both the continuous Riemannian gradient flow and its discrete companion via the exponential map converge linearly to the unique subproblem minimizer. Propagating finite-time inner-solver inexactness and neural-approximation error through the MMS iterations yields a uniform function-space tracking bound and an explicit trajectory budget, so the inexact neural iterates converge to an $O(δ)$-neighborhood of the global minimum. Numerical experiments on nonlinear regression and a small-scale latent-diffusion testbed indicate that the Gauss--Newton-type inner solver achieves smaller trajectory errors with substantially fewer inner iterations than first-order baselines.

math.OC↗

arXiv2026

PINS: Proximal Iterations with Sparse Newton and Sinkhorn for Optimal Transport

Optimal transport (OT) is a widely used tool in machine learning, but computing high-accuracy solutions for large instances remains costly. Entropic regularization and the Sinkhorn algorithm improve scalability; however, when the regularization parameter is small, Sinkhorn convergence slows, and the iterates approach an entropic solution that remains separated from the true OT plan by an entropic-bias plateau. We introduce PINS (Proximal Iterations with sparse Newton and Sinkhorn), a two-loop solver designed to move beyond this plateau. The outer loop applies an entropic proximal-point method, solving the original OT problem through a sequence of entropic subproblems with shifted cost matrices. Each inner subproblem is then solved by a Sinkhorn warm-up followed by sparse-Newton refinement. We prove that PINS converges globally to an optimal solution of the unregularized OT problem and that the inner Hessian admits a sparsification at every outer iteration with a structure independent of the cost matrix. On synthetic and augmented-MNIST instances, PINS achieves much lower relative cost errors than Sinkhorn-type baselines, which stall at the entropic-bias plateau, and is $5$--$73\times$ faster than Sinkhorn with the same outer loop at matched accuracy. On large-scale DOTmark instances, a streaming implementation reduces peak memory by $24$--$54\%$ compared with the network-simplex linear programming (LP) solver and remains feasible under per-process memory budgets for which the LP solver fails.

cs.LG↗

arXiv2026

Finite Expression Method with TranNet-based Function Learning for High-Dimensional Partial Differential Equations

In this paper, we study a machine-learning-based solver for high-dimensional partial differential equations (PDEs). Computing accurate solutions efficiently for such problems remains challenging because of the curse of dimensionality, which severely limits the scalability of classical numerical methods. Our approach builds on the recently developed finite expression method (FEX), which approximates PDE solutions in a function space generated by finitely many analytic expressions. This framework has been shown to achieve high, and in some cases machine-level, accuracy with polynomial memory complexity and favorable computational cost. We propose an extension of FEX in which the functional pool is generated by shallow neural network operators whose parameters are initialized using the transferable neural network method TransNet. Numerical experiments suggest that the proposed extension is an effective alternative for solving several high-dimensional PDEs.

math.NA↗

arXiv2026

Beyond Expected Information Gain: Stable Bayesian Optimal Experimental Design with Integral Probability Metrics and Plug-and-Play Extensions

Bayesian Optimal Experimental Design (BOED) provides a rigorous framework for decision-making tasks in which data acquisition is often the critical bottleneck, especially in resource-constrained settings. Traditionally, BOED typically selects designs by maximizing expected information gain (EIG), commonly defined through the Kullback-Leibler (KL) divergence. However, classical evaluation of EIG often involves challenging nested expectations, and even advanced variational methods leave the underlying log-density-ratio objective unchanged. As a result, support mismatch, tail underestimation, and rare-event sensitivity remain intrinsic concerns for KL-based BOED. To address these fundamental bottlenecks, we introduce an IPM-based BOED framework that replaces density-based divergences with integral probability metrics (IPMs), including the Wasserstein distance, Maximum Mean Discrepancy, and Energy Distance, resulting in a highly flexible plug-and-play BOED framework. We establish theoretical guarantees showing that IPM-based utilities provide stronger geometry-aware stability under surrogate-model error and prior misspecification than classical EIG-based utilities. We also validate the proposed framework empirically, demonstrating that IPM-based designs yield highly concentrated credible sets. Furthermore, by extending the same sample-based BOED template in a plug-and-play manner to geometry-aware discrepancies beyond the IPM class, illustrated by a neural optimal transport estimator, we achieve accurate optimal designs in high-dimensional settings where conventional nested Monte Carlo estimators and advanced variational methods fail.

stat.ML↗

arXiv2026

Randomized Subsystem Descent for Fermion-to-Qubit Mapping

We propose a versatile and efficient algorithmic framework for optimizing fermion-to-qubit mappings by generalizing the idea of randomized block coordinate descent. Our greedy approach, termed Randomized Subsystem Descent, iteratively samples a tractable subsystem from the full Hamiltonian, performs optimization within the subsystem under a given metric, and then reintegrates the updated subsystem into the global operator. Restricting the optimization to a subsystem at each iteration ensures computational efficiency, bypassing the dimensional bottlenecks that usually hinder global search heuristics. We benchmark our algorithm on one- and two-dimensional lattice hopping models, the Hubbard model with up to $16 \times 16$ sites, alongside a collection of molecular electronic-structure Hamiltonians with up to 54 modes and more than 180,000 Pauli strings. Across all benchmarks, our method consistently provides appreciable reduction in (weighted) Pauli weight, suggesting that Randomized Subsystem Descent is a practical and scalable framework for lowering the resource overhead of finding hardware-efficient Hamiltonian encodings.

quant-ph↗

arXiv2026

Principal Prototype Analysis on Manifold for Interpretable Reinforcement Learning

Recent years have witnessed the widespread adoption of reinforcement learning (RL), from solving real-time games to fine-tuning large language models using human preference data significantly improving alignment with user expectations. However, as model complexity grows exponentially, the interpretability of these systems becomes increasingly challenging. While numerous explainability methods have been developed for computer vision and natural language processing to elucidate both local and global reasoning patterns, their application to RL remains limited. Direct extensions of these methods often struggle to maintain the delicate balance between interpretability and performance within RL settings. Prototype-Wrapper Networks (PW-Nets) have recently shown promise in bridging this gap by enhancing explainability in RL domains without sacrificing the efficiency of the original black-box models. However, these methods typically require manually defined reference prototypes, which often necessitate expert domain knowledge. In this work, we propose a method that removes this dependency by automatically selecting optimal prototypes from the available data. Preliminary experiments on standard Gym environments demonstrate that our approach matches the performance of existing PW-Nets, while remaining competitive with the original black-box models.

cs.LG↗

arXiv2026

Quantum Circuit Encodings of Polynomial Chaos Expansions

This work investigates the expressive power of quantum circuits in approximating high-dimensional, real-valued functions. We focus on countably-parametric holomorphic maps $u:U\to \mathbb{R}$, where the parameter domain is $U=[-1,1]^{\mathbb{N}}$. We establish dimension-independent quantum circuit approximation rates via the best $n$-term truncations of generalized polynomial chaos (gPC) expansions of these parametric maps, demonstrating that these rates depend solely on the summability exponent of the gPC expansion coefficients. The key to our findings is based on the fact that so-called ``$(\boldsymbol{b},ε)$-holomorphic'' functions, where $\boldsymbol{b}\in (0,1]^\mathbb N \cap \ell^p(\mathbb N)$ for some $p\in(0,1)$, permit structured and sparse gPC expansions. Then, $n$-term truncated gPC expansions are known to admit approximation rates of order $n^{-1/p + 1/2}$ in the $L^2$ norm and of order $n^{-1/p + 1}$ in the $L^\infty$ norm. We show the existence of parameterized quantum circuit (PQC) encodings of these $n$-term truncated gPC expansions, and bound PQC depth and width via (i) tensorization of univariate PQCs that encode Chebyšev-polynomials in $[-1,1]$ and (ii) linear combination of unitaries (LCU) to build PQC emulations of $n$-term truncated gPC expansions. The results provide a rigorous mathematical foundation for the use of quantum algorithms in high-dimensional function approximation. As countably-parametric holomorphic maps naturally arise in parametric PDE models and uncertainty quantification (UQ), our results have implications for quantum-enhanced algorithms for a wide range of maps in applications.

math.NA↗

arXiv2026

Non-Uniform Quantum Fourier Transform

The Discrete Fourier Transform (DFT) is central to the analysis of uniformly sampled signals, yet many practical applications involve non-uniform sampling, requiring the Non-Uniform Discrete Fourier Transform (NUDFT). While quantum algorithms for the standard DFT are well established, a corresponding framework for the non-uniform case remains underdeveloped. This work introduces a quantum algorithm for the Non-Uniform Quantum Fourier Transform (NUQFT) based on a low-rank factorization of the NUDFT matrix. The factorization is translated into an explicit quantum construction using block encodings, Quantum Signal Processing, and the Linear Combination of Unitaries framework, yielding an $ε$-accurate block encoding of the NUDFT matrix with controlled approximation error from both classical truncation and quantum implementation. Under standard oracle access assumptions for non-uniform sampling points, we derive explicit, non-asymptotic gate-level resource estimates. The resulting complexity scales polylogarithmically with target precision, quadratically with the number of qubits through the quantum Fourier transform, and logarithmically with a geometry-dependent conditioning parameter induced by the non-uniform grid. This establishes a concrete and resource-efficient quantum analogue of the NUDFT and provides a foundation for quantum algorithms on irregularly sampled data.

quant-ph↗

arXiv2026

Curse of Dimensionality in Neural Network Optimization

This paper demonstrates that when a shallow neural network with a Lipschitz continuous activation function is trained using either empirical or population risk to approximate a target function that is $r$ times continuously differentiable on $[0,1]^d$, the population risk may not decay at a rate faster than $t^{-\frac{4r}{d-2r}}$, where $t$ denotes the time parameter of the gradient flow dynamics. This result highlights the presence of the curse of dimensionality in the optimization computation required to achieve a desired accuracy. Instead of analyzing parameter evolution directly, the training dynamics are examined through the evolution of the parameter distribution under the 2-Wasserstein gradient flow. Furthermore, it is established that the curse of dimensionality persists when a locally Lipschitz continuous activation function is employed, where the Lipschitz constant in $[-x,x]$ is bounded by $O(x^δ)$ for any $x \in \mathbb{R}$. In this scenario, the population risk is shown to decay at a rate no faster than $t^{-\frac{(4+2δ)r}{d-2r}}$. Understanding how function smoothness influences the curse of dimensionality in neural network optimization theory is an important and underexplored direction that this work aims to address.

cs.LG↗

arXiv2026

FMint-SDE: A Multimodal Foundation Model for Accelerating Numerical Simulation of SDEs via Error Correction

Fast and accurate simulation of dynamical systems is a fundamental challenge across scientific and engineering domains. Traditional numerical integrators often face a trade-off between accuracy and computational efficiency, while existing neural network-based approaches typically require training a separate model for each case. To overcome these limitations, we introduce a novel multi-modal foundation model for large-scale simulations of differential equations: FMint-SDE (Foundation Model based on Initialization for stochastic differential equations). Based on a decoder-only transformer with in-context learning, FMint-SDE leverages numerical and textual modalities to learn a universal error-correction scheme. It is trained using prompted sequences of coarse solutions generated by conventional solvers, enabling broad generalization across diverse systems. We evaluate our models on a suite of challenging SDE benchmarks spanning applications in molecular dynamics, mechanical systems, finance, and biology. Experimental results show that our approach achieves a superior accuracy-efficiency tradeoff compared to classical solvers, underscoring the potential of FMint-SDE as a general-purpose simulation tool for dynamical systems.

cs.CE↗

arXiv2026

ReSearch: A Multi-Stage Machine Learning Framework for Earth Science Data Discovery

The rapid expansion of Earth Science data from satellite observations, reanalysis products, and numerical simulations has created a critical bottleneck in scientific discovery, namely identifying relevant datasets for a given research objective. Existing discovery systems are primarily retrieval-centric and struggle to bridge the gap between high-level scientific intent and heterogeneous metadata at scale. We introduce \textbf{ReSearch}, a multi-stage, reasoning-enhanced search framework that formulates Earth Science data discovery as an iterative process of intent interpretation, high-recall retrieval, and context-aware ranking. ReSearch integrates lexical search, semantic embeddings, abbreviation expansion, and large language model reranking within a unified architecture that explicitly separates recall and precision objectives. To enable realistic evaluation, we construct a literature-grounded benchmark by aligning natural language intent with datasets cited in peer-reviewed Earth Science studies. Experiments demonstrate that ReSearch consistently improves recall and ranking performance over baseline methods, particularly for task-based queries expressing abstract scientific goals. These results demonstrate the importance of intent-aware, multi-stage search as a foundational capability for reproducible and scalable Earth Science research.

cs.DB↗

arXiv2026

AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing

PDEs are central to scientific and engineering modeling, yet designing accurate numerical solvers typically requires substantial mathematical expertise and manual tuning. Recent neural network-based approaches improve flexibility but often demand high computational cost and suffer from limited interpretability. We introduce \texttt{AutoNumerics}, a multi-agent framework that autonomously designs, implements, debugs, and verifies numerical solvers for general PDEs directly from natural language descriptions. Unlike black-box neural solvers, our framework generates transparent solvers grounded in classical numerical analysis. We introduce a coarse-to-fine execution strategy and a residual-based self-verification mechanism. Experiments on 24 canonical and real-world PDE problems demonstrate that \texttt{AutoNumerics} achieves competitive or superior accuracy compared to existing neural and LLM-based baselines, and correctly selects numerical schemes based on PDE structural properties, suggesting its viability as an accessible paradigm for automated PDE solving.

cs.AI↗

arXiv2026

Data Completion for Electrical Impedance Tomography by Conditional Diffusion Models

Data scarcity is a fundamental barrier in Electrical Impedance Tomography (EIT), as undersampled Dirichlet-to-Neumann (DtN) measurements can substantially degrade conductivity reconstructions. We address this bottleneck by completing partially observed DtN measurements using a diffusion based generative model. Specifically, we train a conditional diffusion model to learn the distribution of DtN data and to infer full measurement vectors given partial observations. Our approach supports flexible source receiver configurations and can be used as a plug in preprocessing step with off the shelf EIT solvers. Under mild assumptions on the polygon conductivity class, we derive nonasymptotic end to end bounds on the distributional discrepancy between the completed and ground truth DtN measurements. In numerical experiments, we couple the proposed diffusion completion procedure with a deep learning based inverse solver and compare its performance against the same solver with full measurement data. The results show that diffusion completion enables reconstructions comparable to the full data baseline while using only 1% of the measurements. In contrast, standard baselines such as matrix completion require 30% of the measurements to achieve similar reconstruction quality.

math.NA↗

arXiv2026

DRIFT: Detecting Representational Inconsistencies for Factual Truthfulness

LLMs often produce fluent but incorrect answers, yet detecting such hallucinations typically requires multiple sampling passes or post-hoc verification, adding significant latency and cost. We hypothesize that intermediate layers encode confidence signals that are lost in the final output layer, and propose a lightweight probe to read these signals directly from hidden states. The probe adds less than 0.1\% computational overhead and can run fully in parallel with generation, enabling hallucination detection before the answer is produced. Building on this, we develop an LLM router that answers confident queries immediately while delegating uncertain ones to stronger models. Despite its simplicity, our method achieves SOTA AUROC on 10 out of 12 settings across four QA benchmarks and three LLM families, with gains of up to 13 points over prior methods, and generalizes across dataset shifts without retraining.

cs.CL↗

arXiv2026

Reinforced Inverse Scattering

Inverse wave scattering aims at determining the properties of an object using data on how the object scatters incoming waves. In order to collect information, sensors are put in different locations to send and receive waves from each other. The choice of sensor positions and incident wave frequencies determines the reconstruction quality of scatterer properties. This paper introduces reinforcement learning to develop precision imaging that decides sensor positions and wave frequencies adaptive to different scatterers in an intelligent way, thus obtaining a significant improvement in reconstruction quality with limited imaging resources. Extensive numerical results will be provided to demonstrate the superiority of the proposed method over existing methods.

cs.LG↗

arXiv2026

Finite Expression Methods for Discovering Physical Laws from Data

Nonlinear dynamics is a pervasive phenomenon observed in scientific and engineering disciplines. However, the task of deriving analytical expressions to describe nonlinear dynamics from limited data remains challenging. In this paper, we shall present a novel deep symbolic learning method called the "finite expression method" (FEX) to discover governing equations within a function space containing a finite set of analytic expressions, based on observed dynamic data. The key concept is to employ FEX to generate analytical expressions of the governing equations by learning the derivatives of partial differential equation (PDE) solutions through convolutions. Our numerical results demonstrate that our FEX surpasses other existing methods (such as PDE-Net, SINDy, GP, and SPL) in terms of numerical performance across a range of problems, including time-dependent PDE problems and nonlinear dynamical systems with time-varying coefficients. Moreover, the results highlight FEX's flexibility and expressive power in accurately approximating symbolic governing equations.

cs.LG↗