8 papers
A Unified Descriptive-Complexity Framework for Model Selection under Correlated Designs
Yanhang Zhang, Wei Liu, Yuhong Yang
Model selection becomes particularly challenging under strong predictor dependence and model-class uncertainty, especially when there are exponentially many models. We propose a De…
Learning Joint Graphical Model with Computational Efficiency, Dynamic Regularization, and Adaptation
Shixiang Liu, Yanhang Zhang, Zhifan Li +1
Multi-sourced datasets are common in studies of variable interactions, for example, heterogeneous gene networks, cross-domain recommendation, etc., where each source induces a rela…
Rethinking Hard Thresholding Pursuit: Full Adaptation and Sharp Estimation
Yanhang Zhang, Zhifan Li, Shixiang Liu +2
Hard Thresholding Pursuit (HTP) has aroused increasing attention for its robust theoretical guarantees and impressive numerical performance in non-convex optimization. In this pape…
Exact recovery in the double sparse model: sufficient and necessary signal conditions
Shixiang Liu, Zhifan Li, Yanhang Zhang +1
The double sparse linear model, which has both group-wise and element-wise sparsity in regression coefficients, has attracted lots of attention recently. This paper establishes the…
Sharp minimax optimality of LASSO and SLOPE under double sparsity assumption
Zhifan Li, Yanhang Zhang, Jianxin Yin
This paper introduces a rigorous approach to establish the sharp minimax optimalities of both LASSO and SLOPE within the framework of double sparse structures, notably without rely…
A minimax optimal approach to high-dimensional double sparse linear regression
Yanhang Zhang, Zhifan Li, Shixiang Liu +1
In this paper, we focus our attention on the high-dimensional double sparse linear regression, that is, a combination of element-wise and group-wise sparsity. To address this probl…
Minimax Rates for High-dimensional Double Sparse Structure over -balls
Zhifan Li, Yanhang Zhang, Jianxin Yin
In this paper, we focus on the high-dimensional double sparse structure, where the parameter of interest simultaneously encourages group-wise sparsity and element-wise sparsity in…
V-Doc : Visual questions answers with Documents
Yihao Ding, Zhe Huang, Runlin Wang +5
We propose V-Doc, a question-answering tool using document images and PDF, mainly for researchers and general non-deep learning experts looking to generate, process, and understand…