12 papers
MG-SpaIR: Multi-grade Sparse-guided Implicit Representation for Training-Data-Free Image Restoration
Jianmin Liao, Lei Huang, Ronglong Fang +3
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 o…
Oracle Supervision Transfers for Hyperparameter Prediction in Model-Based Image Denoising
Jianmin Liao, Lixin Shen, Yuesheng Xu
Hyperparameter prediction is a critical practical bottleneck for model-based image denoisers, ranging from classical TV/TGV variational solvers to modern diffusion-based models suc…
Multigrade Neural Network Approximation
Shijun Zhang, Zuowei Shen, Yuesheng Xu
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…
Online Learning of HTN Methods for integrated LLM-HTN Planning
Yuesheng Xu, Hector Munoz-Avila
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 t…
Computational Advantages of Multi-Grade Deep Learning: Convergence Analysis and Performance Insights
Ronglong Fang, Yuesheng Xu
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 investigat…
Sparsity-Guided Multi-Parameter Selection in -Regularized Models via a Fixed-Point Proximity Approach
Qianru Liu, Rui Wang, Yuesheng Xu
We study a regularization framework that combines a convex fidelity term with multiple -based regularizers, each linked to a distinct linear transform. This multi-penalty m…
Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning
Ronglong Fang, Yuesheng Xu
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, struggl…
A Dynamic Weighting Strategy to Mitigate Worker Node Failure in Distributed Deep Learning
Yuesheng Xu, Arielle Carr
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…
Sparse Deep Learning Models with the Regularization
Lixin Shen, Rui Wang, Yuesheng Xu +1
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 s…
Inexact FPPA for the Sparse Regularization Problem
Ronglong Fang, Yuesheng Xu, Mingsong Yan
We study inexact fixed-point proximity algorithms for solving a class of sparse regularization problems involving the norm. Specifically, the model has an objecti…
Hypothesis Spaces for Deep Learning
Rui Wang, Yuesheng Xu, Mingsong Yan
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 param…
A Duality Approach to Regularized Learning Problems in Banach Spaces
Raymond Cheng, Rui Wang, Yuesheng Xu
Learning methods in Banach spaces are often formulated as regularization problems which minimize the sum of a data fidelity term in a Banach norm and a regularization term in anoth…