Search Results for author: Xiaoqun Zhang

Found 10 papers, 6 papers with code

Large Language Models as Surrogate Models in Evolutionary Algorithms: A Preliminary Study

1 code implementation15 Jun 2024 Hao Hao, Xiaoqun Zhang, Aimin Zhou

Specifically, we formulate model-assisted selection as a classification and regression problem, utilizing LLMs to directly evaluate the quality of new solutions based on historical data.

Evolutionary Algorithms

A First Look at Kolmogorov-Arnold Networks in Surrogate-assisted Evolutionary Algorithms

1 code implementation26 May 2024 Hao Hao, Xiaoqun Zhang, Bingdong Li, Aimin Zhou

We employ KANs for regression and classification tasks, focusing on the selection of promising solutions during the search process, which consequently reduces the number of expensive function evaluations.

Evolutionary Algorithms

Model Uncertainty in Evolutionary Optimization and Bayesian Optimization: A Comparative Analysis

2 code implementations21 Mar 2024 Hao Hao, Xiaoqun Zhang, Aimin Zhou

Black-box optimization problems, which are common in many real-world applications, require optimization through input-output interactions without access to internal workings.

Bayesian Optimization

Enhancing SAEAs with Unevaluated Solutions: A Case Study of Relation Model for Expensive Optimization

1 code implementation21 Sep 2023 Hao Hao, Xiaoqun Zhang, Aimin Zhou

Furthermore, the surrogate-selected unevaluated solutions with high potential have been shown to significantly enhance the efficiency of the algorithm.

Evolutionary Algorithms Relation

Arbitrary Distributions Mapping via SyMOT-Flow: A Flow-based Approach Integrating Maximum Mean Discrepancy and Optimal Transport

no code implementations26 Aug 2023 Zhe Xiong, Qiaoqiao Ding, Xiaoqun Zhang

Finding a transformation between two unknown probability distributions from finite samples is crucial for modeling complex data distributions and performing tasks such as sample generation, domain adaptation and statistical inference.

Density Estimation Domain Adaptation +2

NF-ULA: Langevin Monte Carlo with Normalizing Flow Prior for Imaging Inverse Problems

1 code implementation17 Apr 2023 Ziruo Cai, Junqi Tang, Subhadip Mukherjee, Jinglai Li, Carola Bibiane Schönlieb, Xiaoqun Zhang

Bayesian methods for solving inverse problems are a powerful alternative to classical methods since the Bayesian approach offers the ability to quantify the uncertainty in the solution.

Bayesian Inference Computed Tomography (CT) +4

A Dataset-free Deep learning Method for Low-Dose CT Image Reconstruction

no code implementations1 May 2022 Qiaoqiao Ding, Hui Ji, Yuhui Quan, Xiaoqun Zhang

Low-dose CT (LDCT) imaging attracted a considerable interest for the reduction of the object's exposure to X-ray radiation.

Bayesian Inference Image Reconstruction

Semi-Implicit Back Propagation

no code implementations10 Feb 2020 Ren Liu, Xiaoqun Zhang

Neural network has attracted great attention for a long time and many researchers are devoted to improve the effectiveness of neural network training algorithms.

An Edge Driven Wavelet Frame Model for Image Restoration

no code implementations25 Jan 2017 Jae Kyu Choi, Bin Dong, Xiaoqun Zhang

Wavelet frame systems are known to be effective in capturing singularities from noisy and degraded images.

Deblurring Image Inpainting +1

Cannot find the paper you are looking for? You can Submit a new open access paper.