Posts by Collection

publications

A Local Existence Theorem for a Parabolic Blow-Up Inverse Problem.

Published in Pure Mathematics, 2017

Recommended citation: Yu Pan, Xuran Meng and Wuqing Ning, "A Local Existence Theorem for a Parabolic Blow-Up Inverse Problem." Pure Mathematics, 2017.
Download Paper

High frequency algorithm and its back-testing results based on GAN.

Published in JUSTC, 2020

Recommended citation: Xuran Meng, Xiuchun Bi and Shuguang Zhang, "High frequency algorithm and its back-testing results based on GAN." JUSTC 50, 2020.
Download Paper

l1–2 minimisation for compressed sensing with partially known signal support.

Published in Electronics Letters, 2020

Recommended citation: Jing Zhang, Shuguang Zhang and Xuran Meng, "l1–2 minimisation for compressed sensing with partially known signal support." Electronics Letters 56, 2020.
Download Paper

Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping.

Published in Journal of Machine Learning Research, 2023

Recommended citation: Xuran Meng and Jianfeng Yao, "Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping." JMLR 24, 2023.
Download Paper | Download Slides

Multiple Descent in the Multiple Random Feature Model.

Published in Journal of Machine Learning Research, 2024

Recommended citation: Xuran Meng, Jianfeng Yao and Yuan Cao, "Multiple Descent in the Multiple Random Feature Model." JMLR 25, 2024.
Download Paper | Download Slides

Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data.

Published in International Conference on Machine Learning, 2024

Recommended citation: Xuran Meng, Difan Zou and Yuan Cao, "Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data." ICML, 2024.
Download Paper

Estimation of Out-of-Sample Sharpe Ratio for High Dimensional Portfolio Optimization.

Published in Arxiv, 2024

Submitted to JASA

Recommended citation: Xuran Meng, Yuan Cao and Weichen Wang, "Estimation of Out-of-Sample Sharpe Ratio for High Dimensional Portfolio Optimization." arxiv: 2406.03954, 2024.
Download Paper

Initialization Matters: On the Benign Overfitting of Two-Layer ReLU CNN with Fully Trainable Layers.

Published in Arxiv, 2024

Submitted to JMLR

Recommended citation: Shuning Shang, Xuran Meng, Yuan Cao and Difan Zou, "Initialization Matters: On the Benign Overfitting of Two-Layer ReLU CNN with Fully Trainable Layers." arxiv: 2410.19139, 2024.
Download Paper

Statistical Inference on High Dimensional Gaussian Graphical Regression Models.

Published in Arxiv, 2024

Submitted to JASA

Recommended citation: Xuran Meng, Jingfei Zhang and Yi Li, "Statistical Inference on High Dimensional Gaussian Graphical Regression Models." arxiv: 2411.01588, 2024.
Download Paper

Per-Example Gradient Regularization Improves Learning Signals from Noisy Data.

Published in Machine Learning, 2025

Machine Learning

Recommended citation: Xuran Meng, Yuan Cao and Difan Zou, "Per-Example Gradient Regularization Improves Learning Signals from Noisy Data." Machine Learning, 2025.
Download Paper

Transformer learns optimal variable selection in group-sparse classification.

Published in International Conference on Learning Representations, 2025

Recommended citation: Chenyang Zhang, Xuran Meng and Yuan Cao, "Transformer learns optimal variable selection in group-sparse classification." ICLR, 2025.
Download Paper

Inferring Outcome Means of Exponential Family Distributions Estimated by Deep Neural Networks.

Published in Arxiv, 2025

Submitted to AOS

Recommended citation: Xuran Meng and Yi Li, "Inferring Outcome Means of Exponential Family Distributions Estimated by Deep Neural Networks." arxiv: 2504.09347, 2024.
Download Paper

teaching

Tutor from 2020-2024

Undergraduate/Postgraduate course, University of Hong Kong, Department of Statistics and Actuarial Science, 2020

Stochastic Process, Financial Economics, Bayesian Learning

Xuran Meng

Posts by Collection

publications

A Local Existence Theorem for a Parabolic Blow-Up Inverse Problem.

High frequency algorithm and its back-testing results based on GAN.

l1–2 minimisation for compressed sensing with partially known signal support.

Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping.

Multiple Descent in the Multiple Random Feature Model.

Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data.

Estimation of Out-of-Sample Sharpe Ratio for High Dimensional Portfolio Optimization.

Initialization Matters: On the Benign Overfitting of Two-Layer ReLU CNN with Fully Trainable Layers.

Statistical Inference on High Dimensional Gaussian Graphical Regression Models.

Per-Example Gradient Regularization Improves Learning Signals from Noisy Data.

Transformer learns optimal variable selection in group-sparse classification.

Inferring Outcome Means of Exponential Family Distributions Estimated by Deep Neural Networks.

talks

Poster in RMTA 2023

Poster in ICML 2024

OCPS in the 11th World Congress in Probability and Statistics

teaching

Tutor from 2020-2024