Searcharxiv⌕ Search

arXiv subjects

Yuesheng Xu

Publications and source records attributed to Yuesheng Xu.

At least 19 recordsLinked to original sources

Layer-wise Geometric Approximation Rates for Deep Networks

Depth is widely viewed as a central contributor to the success of deep neural networks, yet standard approximation results typically give error bounds only for the final output of a network. Inspired by classical multiscale expansions and multigrade deep learning, we give depth a scale-dependent interpretation by constructing a single network whose intermediate readouts approximate the target at successively finer scales. For any $f\in L^p([0,1]^d)$ with $1\le p <\infty$ and any integer $N\ge2$, we construct a single network of width $3dN+2d+4$ with the same activation pattern in every hidden layer, using sine in the first two neurons and $\mathtt{ReLU}$ in the rest. For every $\ell\ge0$, the $L^p$ approximation error of the readout $Φ_\ell$ at layer $\ell+4$ is bounded by $(2d+1)ω_{f,p}(N^{-\ell})$, where $ω_{f,p}$ denotes the $L^p$ translation modulus of $f$. Under the Hölder condition $ω_{f,p}(t)\le Ct^α$ with $C>0$ and $0< α\le 1$, this estimate yields the geometric bound $(2d+1)C N^{-α\ell}$. More generally, if $ω_{f,p}(t)$ has a known upper bound that tends to zero as $t\downarrow0$, we obtain a stopping rule for adaptive depth selection. We can stop at the first depth where the error bound meets the desired tolerance and later append layers to meet a tighter tolerance while keeping all earlier maps and readouts fixed.

cs.LG↗

SPLAT: An Event-Specific System Response Model for Continuous-Domain List-Mode TOF PET

Modern position-sensitive PET detectors provide continuous estimates of photon interaction position and event-specific timing, energy, and depth-of-interaction (DOI) information. We introduce Spatial Probability Localization and Transformation (SPLAT), a continuous-domain, event-specific projection model for time-of-flight (TOF) list-mode PET. Each coincidence is represented by a three-dimensional spatial response kernel incorporated into consistent forward and adjoint operators without detector-coordinate binning. While supporting general response distributions, we develop an anisotropic Gaussian implementation whose center is determined by measured interaction positions and TOF difference, and whose full covariance follows from propagating measurement uncertainties through event geometry. The model accounts for DOI, photon non-collinearity, and energy-dependent, correlated, and depth-dependent detector responses. Using GATE Monte Carlo simulations with known annihilation positions, we compare continuous and virtually segmented representations of identical accepted coincidences. Event-localization diagnostics and point-source and brain-phantom reconstructions assess model accuracy and image formation. The Gaussian formulation also yields information-equivalent count gain, an approximate measure of relative spatial information accounting for localization uncertainty and detection efficiency. Results support the value of event-specific modeling, particularly measured DOI, while an optimized GPU implementation demonstrates computational feasibility. SPLAT provides a flexible framework for incorporating detailed detector measurements directly into PET reconstruction.

physics.med-ph↗

Oracle Supervision Transfers for Hyperparameter Prediction in Model-Based Image Denoising

Hyperparameter prediction is a critical practical bottleneck for model-based image denoisers, ranging from classical TV/TGV variational solvers to modern diffusion-based models such as DiffPIR. While existing learned predictors can achieve near-oracle performance, this approach scales poorly: each new configuration conventionally requires its own oracle-labeled training set, and each label requires a hierarchical grid search evaluated against clean ground truth. We therefore ask whether oracle supervision collected on source configurations can transfer to target configurations with few or no target oracle labels. We propose HyperDn, a single configuration-conditioned predictor that pools oracle supervision across source configurations and predicts heterogeneous hyperparameters for new denoiser--noise configurations. In a cross-paradigm experiment, HyperDn transfers from relatively cheap TV/TGV variational sources to more expensive diffusion-based DiffPIR. With only $2$ target oracle labels, it reaches $30.23$\,dB, within $0.90$\,dB of the oracle, and outperforms the $64$-label per-configuration predictor trained from scratch, using $1/32$ as many target labels as that baseline point. Without any target oracle labels, HyperDn also reaches near-oracle PSNR on two unseen mixtures of seen noise types and on transfer from relatively cheap $96\times 96$ source images to $512\times 768$ targets. Together, these results show that expensive oracle supervision for hyperparameter prediction can be transferred from source to new target configurations, reducing the need to rebuild oracle labels for each new denoising configuration.

cs.CV↗

Multigrade Neural Network Approximation

We study multigrade deep learning (MGDL) as a principled framework for structured error refinement in deep neural networks. While the approximation power of neural networks is now relatively well understood, training very deep architectures remains challenging due to highly nonconvex and often ill-conditioned optimization landscapes. In contrast, for relatively shallow networks, most notably certain one-hidden-layer ReLU models, training admits convex reformulations with global guarantees under appropriate settings, motivating learning paradigms that improve stability while scaling to depth. MGDL builds on this insight by training deep networks grade by grade: previously learned grades are frozen, and each newly added grade-wise subnetwork is composed on top of the previously learned grades and trained to fit the residual left by the current approximation, yielding a structured and interpretable hierarchical refinement process. We develop an operator-theoretic foundation for MGDL and prove that, for any continuous target function defined on a hypercube, there exists a fixed-width multigrade ReLU scheme whose residuals are pointwise nonincreasing in magnitude and converge uniformly to zero, with strict $L^p$-norm decay at every nontrivial grade for $p\in [1,\infty)$. To the best of our knowledge, this work provides the first rigorous constructive approximation guarantee showing that a grade-wise residual refinement scheme can achieve vanishing error in a fixed-width multigrade ReLU architecture.

cs.LG↗

Curriculum-Guided Acquisition of Hierarchical Task Knowledge from LLM-Generated Experience

Hierarchical task knowledge enables efficient problem solving by allowing previously acquired skills to be reused across tasks and problem instances. In this paper, we investigate curriculum-guided acquisition of hierarchical task knowledge in an HTN learning framework. We compare three approaches: online learning during problem solving, human-designed curricula, and an automated curriculum generation procedure that derives learning experiences from verified LLM-generated solution traces. The proposed procedure solves small training problems with an LLM, extracts task accomplishment information, and transforms it into ordered sequences of state-task learning problems for HTN method acquisition. We evaluate the three approaches across multiple planning domains. The results demonstrate that automatically generated curricula recover much of the benefit of expert-designed curricula while substantially reducing the token cost of online hierarchical knowledge acquisition.

cs.AI↗

The Adaptive Solution of High-Frequency Helmholtz Equations via Multi-Grade Deep Learning

The Helmholtz equation is fundamental for modeling wave propagation in acoustics, electromagnetics, and geophysics; however, high-frequency regimes remain notoriously difficult due to the severe numerical ``pollution effect.'' We propose FD-MGDL, an adaptive framework that synergizes finite difference discretizations with Multi-Grade Deep Learning (MGDL) to efficiently resolve high-frequency wavefields. Unlike standard physics-informed neural networks (PINNs), which frequently suffer from spectral bias and heavy automatic differentiation overhead, FD-MGDL employs a progressive, grade-wise training strategy that incrementally incorporates shallow sub-networks to refine residual errors. By leveraging ReLU activations in refinement grades, the framework reformulates the highly non-convex global optimization problem into a sequence of tractable convex subproblems, dramatically improving training stability and convergence reliability. Extensive numerical experiments in two and three dimensions with wavenumbers up to $κ=200$ demonstrate that FD-MGDL significantly outperforms single-grade networks and standard benchmark neural solvers in both accuracy and computational efficiency. When applied to an inhomogeneous concave velocity model, the proposed method accurately captures wave focusing and caustic formations, markedly outperforming classical five-point finite difference schemes in resolving sharp phase transitions and peak amplitudes. These results establish FD-MGDL as a robust, scalable, and mathematically grounded paradigm for high-frequency wave simulation in complex media.

math.NA↗

MG-SpaIR: Multi-grade Sparse-guided Implicit Representation for Training-Data-Free Image Restoration

MG-SpaIR is a training-data-free framework for restoring a clean image from a single observation corrupted by a mixture of blur, downsampling, noise, and missing pixels. Building on implicit neural representations (INRs), we introduce a multi-grade coarse-to-fine residual hierarchy that progressively refines the reconstruction across resolution grades, improving representational fidelity and mitigating spectral limitations. To stabilize reconstruction optimization and suppress INR-induced artifacts, we further propose an explicit sparse proximal regularization (e.g., $\ell_0$-type) applied directly in the high-resolution image domain, which discourages spurious high-frequency patterns while preserving sharp structures. The resulting optimization is solved efficiently via a multi-grade proximal alternating scheme, and we establish convergence guarantees for the associated updates under standard regularity conditions. Experiments on mixed-degradation benchmarks demonstrate that MG-SpaIR consistently outperforms strong training-data-free baselines such as Deep Image Prior, providing a stable, interpretable, and data-efficient alternative to conventional learning-based restoration methods.

cs.CV↗

Multi-Grade Deep Learning for Partial Differential Equations with Applications to the Burgers Equation

Deep neural networks (DNNs) show great promise for solving partial differential equations (PDEs), but their deep architectures introduce complex, large-scale, non-convex optimization challenges. Nonlinear PDEs, like the viscous Burgers' equation, compound these difficulties due to steep gradients and shock-like solutions. To address this, we propose a two-stage multi-grade deep learning (TS-MGDL) method. In the first stage, shallow networks are trained progressively grade by grade to fit the target function from low- to high-frequency components; previously learned grades are frozen, and each new residual block is trained solely to minimize the remaining approximation error. The second stage unfreezes and retrains selected layers using the first-stage network as initialization, achieving an interpretable, stable hierarchical refinement while mitigating optimization complexity. Furthermore, we theoretically prove that each grade and stage in TS-MGDL monotonically reduces the loss function under an appropriate optimization strategy. Numerical experiments on 1D, 2D, and 3D viscous Burgers' equations demonstrate that TS-MGDL significantly outperforms single-grade learning (SGL), reducing predictive errors by up to a factor of 60.

math.NA↗

Sparsity-Guided Multi-Parameter Selection in $\ell_1$-Regularized Models via a Fixed-Point Proximity Approach

We study a regularization framework that combines a convex fidelity term with multiple $\ell_1$-based regularizers, each linked to a distinct linear transform. This multi-penalty model enhances flexibility in promoting structured sparsity. We analyze how the choice of regularization parameters governs the sparsity of solutions under the given transforms and derive a precise relationship between the parameters and resulting sparsity patterns. This insight enables the development of an iterative strategy for selecting parameters to achieve prescribed sparsity levels. A key computational challenge arises in practice: effective parameter tuning requires simultaneous access to the regularized solution and two auxiliary vectors derived from the sparsity analysis. To address this, we propose a fixed-point proximity algorithm that jointly computes all three vectors. Together with our theoretical characterization, this algorithm forms the basis of a practical multi-parameter selection scheme. Numerical experiments demonstrate that the proposed method reliably produces solutions with desired sparsity patterns and strong approximation accuracy.

math.NA↗

Adaptive Multi-Grade Deep Learning for Highly Oscillatory Fredholm Integral Equations of the Second Kind

This paper studies the use of Multi-Grade Deep Learning (MGDL) for solving highly oscillatory Fredholm integral equations of the second kind. We provide rigorous error analyses of continuous and discrete MGDL models, showing that the discrete model retains the convergence and stability of its continuous counterpart under sufficiently small quadrature error. We identify the DNN training error as the primary source of approximation error, motivating a novel adaptive MGDL algorithm that selects the network grade based on training performance. Numerical experiments with highly oscillatory (including wavenumber 500) and singular solutions confirm the accuracy, effectiveness and robustness of the proposed approach.

math.NA↗

Online Learning of HTN Methods for integrated LLM-HTN Planning

We present online learning of Hierarchical Task Network (HTN) methods in the context of integrated HTN planning and LLM-based chatbots. Methods indicate when and how to decompose tasks into subtasks. Our method learner is built on top of the ChatHTN planner. ChatHTN queries ChatGPT to generate a decomposition of a task into primitive tasks when no applicable method for the task is available. In this work, we extend ChatHTN. Namely, when ChatGPT generates a task decomposition, ChatHTN learns from it, akin to memoization. However, unlike memoization, it learns a generalized method that applies not only to the specific instance encountered, but to other instances of the same task. We conduct experiments on two domains and demonstrate that our online learning procedure reduces the number of calls to ChatGPT while solving at least as many problems, and in some cases, even more.

cs.AI↗

Hypothesis Spaces for Deep Learning

This paper introduces a hypothesis space for deep learning based on deep neural networks (DNNs). By treating a DNN as a function of two variables - the input variable and the parameter variable - we consider the set of DNNs where the parameter variable belongs to a space of weight matrices and biases determined by a prescribed depth and layer widths. To construct a Banach space of functions of the input variable, we take the weak* closure of the linear span of this DNN set. We prove that the resulting Banach space is a reproducing kernel Banach space (RKBS) and explicitly construct its reproducing kernel. Furthermore, we investigate two learning models - regularized learning and the minimum norm interpolation (MNI) problem - within the RKBS framework by establishing representer theorems. These theorems reveal that the solutions to these learning problems can be expressed as a finite sum of kernel expansions based on training data.

stat.ML↗

Computational Advantages of Multi-Grade Deep Learning: Convergence Analysis and Performance Insights

Multi-grade deep learning (MGDL) has been shown to significantly outperform the standard single-grade deep learning (SGDL) across various applications. This work aims to investigate the computational advantages of MGDL focusing on its performance in image regression, denoising, and deblurring tasks, and comparing it to SGDL. We establish convergence results for the gradient descent (GD) method applied to these models and provide mathematical insights into MGDL's improved performance. In particular, we demonstrate that MGDL is more robust to the choice of learning rate under GD than SGDL. Furthermore, we analyze the eigenvalue distributions of the Jacobian matrices associated with the iterative schemes arising from the GD iterations, offering an explanation for MGDL's enhanced training stability.

cs.LG↗

Next-Gen Computing Systems with Compute Express Link: a Comprehensive Survey

Interconnection is crucial for computing systems. However, the current interconnection performance between processors and devices, such as memory devices and accelerators, significantly lags behind their computing performance, severely limiting the overall performance. To address this challenge, Intel proposes Compute Express Link (CXL), an open industry-standard interconnection. With memory semantics, CXL offers low-latency, scalable, and coherent interconnection between processors and devices. This paper introduces recent advances in CXL-based computing systems from single-machine to distributed. In single-machine systems, we classify existing research into two categories: Memory Expansion and Unified Memory. Memory Expansion focus on processors and memory, aims to address memory wall challenge. Unified memory focus on processors and accelerators, aims to enhance collaboration in heterogeneous computing systems. In distributed systems, we present how to build efficient disaggregation systems based on CXL infrastructure, enabling resource pooling and sharing. Finally, we discuss the future research and envision memory-centric computing with CXL.

cs.DC↗

Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning

Deep neural networks (DNNs) suffer from the spectral bias, wherein DNNs typically exhibit a tendency to prioritize the learning of lower-frequency components of a function, struggling to capture its high-frequency features. This paper is to address this issue. Notice that a function having only low frequency components may be well-represented by a shallow neural network (SNN), a network having only a few layers. By observing that composition of low frequency functions can effectively approximate a high-frequency function, we propose to learn a function containing high-frequency components by composing several SNNs, each of which learns certain low-frequency information from the given data. We implement the proposed idea by exploiting the multi-grade deep learning (MGDL) model, a recently introduced model that trains a DNN incrementally, grade by grade, a current grade learning from the residue of the previous grade only an SNN composed with the SNNs trained in the preceding grades as features. We apply MGDL to synthetic, manifold, colored images, and MNIST datasets, all characterized by presence of high-frequency features. Our study reveals that MGDL excels at representing functions containing high-frequency information. Specifically, the neural networks learned in each grade adeptly capture some low-frequency information, allowing their compositions with SNNs learned in the previous grades effectively representing the high-frequency features. Our experimental results underscore the efficacy of MGDL in addressing the spectral bias inherent in DNNs. By leveraging MGDL, we offer insights into overcoming spectral bias limitation of DNNs, thereby enhancing the performance and applicability of deep learning models in tasks requiring the representation of high-frequency information. This study confirms that the proposed method offers a promising solution to address the spectral bias of DNNs.

cs.LG↗

A Dynamic Weighting Strategy to Mitigate Worker Node Failure in Distributed Deep Learning

The increasing complexity of deep learning models and the demand for processing vast amounts of data make the utilization of large-scale distributed systems for efficient training essential. These systems, however, face significant challenges such as communication overhead, hardware limitations, and node failure. This paper investigates various optimization techniques in distributed deep learning, including Elastic Averaging SGD (EASGD) and the second-order method AdaHessian. We propose a dynamic weighting strategy to mitigate the problem of straggler nodes due to failure, enhancing the performance and efficiency of the overall training process. We conduct experiments with different numbers of workers and communication periods to demonstrate improved convergence rates and test performance using our strategy.

cs.LG↗

Sparse Deep Learning Models with the $\ell_1$ Regularization

Sparse neural networks are highly desirable in deep learning in reducing its complexity. The goal of this paper is to study how choices of regularization parameters influence the sparsity level of learned neural networks. We first derive the $\ell_1$-norm sparsity-promoting deep learning models including single and multiple regularization parameters models, from a statistical viewpoint. We then characterize the sparsity level of a regularized neural network in terms of the choice of the regularization parameters. Based on the characterizations, we develop iterative algorithms for selecting regularization parameters so that the weight parameters of the resulting deep neural network enjoy prescribed sparsity levels. Numerical experiments are presented to demonstrate the effectiveness of the proposed algorithms in choosing desirable regularization parameters and obtaining corresponding neural networks having both of predetermined sparsity levels and satisfactory approximation accuracy.

cs.LG↗

Inexact FPPA for the $\ell_0$ Sparse Regularization Problem

We study inexact fixed-point proximity algorithms for solving a class of sparse regularization problems involving the $\ell_0$ norm. Specifically, the $\ell_0$ model has an objective function that is the sum of a convex fidelity term and a Moreau envelope of the $\ell_0$ norm regularization term. Such an $\ell_0$ model is non-convex. Existing exact algorithms for solving the problems require the availability of closed-form formulas for the proximity operator of convex functions involved in the objective function. When such formulas are not available, numerical computation of the proximity operator becomes inevitable. This leads to inexact iteration algorithms. We investigate in this paper how the numerical error for every step of the iteration should be controlled to ensure global convergence of the resulting inexact algorithms. We establish a theoretical result that guarantees the sequence generated by the proposed inexact algorithm converges to a local minimizer of the optimization problem. We implement the proposed algorithms for three applications of practical importance in machine learning and image science, which include regression, classification, and image deblurring. The numerical results demonstrate the convergence of the proposed algorithm and confirm that local minimizers of the $\ell_0$ models found by the proposed inexact algorithm outperform global minimizers of the corresponding $\ell_1$ models, in terms of approximation accuracy and sparsity of the solutions.

math.OC↗