activity
20182021
most citedGeneralization bounds for graph convolutional neural networks via Rademacher complexity

4 citations · 5 across the 4 of their papers we have counts for

collaborators

5 papers

math.ST20211 cited

Kernel-based estimation for partially functional linear model: Minimax rates and randomized sketches

Shaogao Lv, Xin He, Junhui Wang

This paper considers the partially functional linear model (PFLM) where all predictive features consist of a functional covariate and a high dimensional scalar vector. Over an infi…

stat.ML20214 cited

Generalization bounds for graph convolutional neural networks via Rademacher complexity

Shaogao Lv

This paper aims at studying the sample complexity of graph convolutional networks (GCNs), by providing tight upper bounds of Rademacher complexity for GCN models with a single hidd…

math.ST2020

Learning rates for partially linear support vector machine in high dimensions

Yifan Xia, Yongchao Hou, Shaogao Lv

This paper analyzes a new regularized learning scheme for high dimensional partially linear support vector machine. The proposed approach consists of an empirical risk and the Lass…

q-fin.CP2019

Financial Market Directional Forecasting With Stacked Denoising Autoencoder

Shaogao Lv, Yongchao Hou, Hongwei Zhou

Forecasting stock market direction is always an amazing but challenging problem in finance. Although many popular shallow computational methods (such as Backpropagation Network and…

stat.ML2018

Efficient kernel-based variable selection with sparsistency

Xin He, Junhui Wang, Shaogao Lv

Variable selection is central to high-dimensional data analysis, and various algorithms have been developed. Ideally, a variable selection algorithm shall be flexible, scalable, an…