collaborators

6 papers

math.OC2026

Exact Instance Compression for Convex Empirical Risk Minimization via Color Refinement

Bryan Zhu, Ziang Chen

Empirical risk minimization (ERM) can be computationally expensive, with standard solvers scaling poorly even in the convex setting. We propose a novel lossless compression framewo…

math.NA2025

Barron Space Representations for Elliptic PDEs with Homogeneous Boundary Conditions

Ziang Chen, Liqiang Huang

We study the complexity of approximating high-dimensional second-order elliptic PDEs with homogeneous boundary conditions on the unit hypercube using Barron spaces. Under suitable…

math.OC2025

Randomized coordinate gradient descent almost surely escapes strict saddle points

Ziang Chen, Yingzhou Li, Zihao Li

We analyze the behavior of randomized coordinate gradient descent for nonconvex optimization, proving that under standard assumptions, the iterates almost surely escape strict sadd…

cs.LG2025

SCFormer: Structured Channel-wise Transformer with Cumulative Historical State for Multivariate Time Series Forecasting

Shiwei Guo, Ziang Chen, Yupeng Ma +2

The Transformer model has shown strong performance in multivariate time series forecasting by leveraging channel-wise self-attention. However, this approach lacks temporal constrai…

cs.LG2025

On the Expressive Power of Subgraph Graph Neural Networks for Graphs with Bounded Cycles

Ziang Chen, Qiao Zhang, Runzhong Wang

Graph neural networks (GNNs) have been widely used in graph-related contexts. It is known that the separation power of GNNs is equivalent to that of the Weisfeiler-Lehman (WL) test…

cs.LG2025

Mean-Field Analysis for Learning Subspace-Sparse Polynomials with Gaussian Input

Ziang Chen, Rong Ge

In this work, we study the mean-field flow for learning subspace-sparse polynomials using stochastic gradient descent and two-layer neural networks, where the input distribution is…