3 papers
cs.LG2026
Transformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression
Mingsong Yan, Dongyang Li, Charles Kulick +1
Mechanistic accounts of in-context learning (ICL) have identified iterative algorithms for linear regression and related linear prediction tasks, often using linear or ReLU attenti…
cs.LG2026
On the Convergence and Size Transferability of Continuous-depth Graph Neural Networks
Mingsong Yan, Charles Kulick, Sui Tang
Continuous-depth graph neural networks, also known as Graph Neural Differential Equations (GNDEs), combine the structural inductive bias of Graph Neural Networks (GNNs) with the co…
stat.ML2025
Data-driven Learning of Interaction Laws in Multispecies Particle Systems with Gaussian Processes: Convergence Theory and Applications
Jinchao Feng, Charles Kulick, Sui Tang
We develop a Gaussian process framework for learning interaction kernels in multi-species interacting particle systems from trajectory data. Such systems provide a canonical settin…