Search Results for author:
Found 14 papers, 5 papers with code
Analysis of Deep Image Prior and Exploiting Self-Guidance for Image Reconstruction
In this work, we first provide an analysis of how DIP recovers information from undersampled imaging measurements by analyzing the training dynamics of the underlying networks in the kernel regime for different architectures.
A Data Generation Perspective to the Mechanism of In-Context Learning
In-Context Learning (ICL) empowers Large Language Models (LLMs) with the capacity to learn in context, achieving downstream generalization without gradient updates but with a few in-context examples.
PAC-tuning:Fine-tuning Pretrained Language Models with PAC-driven Perturbed Gradient Descent
Fine-tuning pretrained language models (PLMs) for downstream tasks is a large-scale optimization problem, in which the choice of the training algorithm critically determines how well the trained model can generalize to unseen test data, especially in the context of few-shot learning.
Robust Physics-based Deep MRI Reconstruction Via Diffusion Purification
In particular, we present a robustification strategy that improves the resilience of DL-based MRI reconstruction methods by utilizing pretrained diffusion models as noise purifiers.
Unlocking Tuning-free Generalization: Minimizing the PAC-Bayes Bound with Trainable Priors
It is widely recognized that the generalization ability of neural networks can be greatly enhanced through carefully designing the training procedure.
Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent
It is well known that the finite step-size ($h$) in Gradient Descent (GD) implicitly regularizes solutions to flatter minima.
Neural Network Approximation of Continuous Functions in High Dimensions with Applications to Inverse Problems
The approach is based on the observation that the existence of a Johnson-Lindenstrauss embedding $A\in\mathbb{R}^{d\times D}$ of a given high-dimensional set $S\subset\mathbb{R}^D$ into a low dimensional cube $[-M, M]^d$ implies that for any H\"older (or uniformly) continuous function $f:S\to\mathbb{R}^p$, there exists a H\"older (or uniformly) continuous function $g:[-M, M]^d\to\mathbb{R}^p$ such that $g(Ax)=f(x)$ for all $x\in S$.
Superiority of GNN over NN in generalizing bandlimited functions
Graph Neural Networks (GNNs) have emerged as formidable resources for processing graph-based information across diverse applications.
Deep Image Matting with Flexible Guidance Input
In this paper, we propose a matting method that use Flexible Guidance Input as user hint, which means our method can use trimap, scribblemap or clickmap as guidance information or even work without any guidance input.
Low-memory stochastic backpropagation with multi-channel randomized trace estimation
Thanks to the combination of state-of-the-art accelerators and highly optimized open software frameworks, there has been tremendous progress in the performance of deep neural networks.
A Hierarchical User Intention-Habit Extract Network for Credit Loan Overdue Risk Detection
In this paper, we propose a model named HUIHEN (Hierarchical User Intention-Habit Extract Network) that leverages the users' behavior information in mobile banking APP.
Linear Convergent Decentralized Optimization with Compression
Communication compression has become a key strategy to speed up distributed optimization.
Manifold Denoising by Nonlinear Robust Principal Component Analysis
This paper extends robust principal component analysis (RPCA) to nonlinear manifolds.
Capacity Preserving Mapping for High-dimensional Data Visualization
We provide a rigorous mathematical treatment to the crowding issue in data visualization when high dimensional data sets are projected down to low dimensions for visualization.
