3 papers
cs.LG2026
Variational Trajectory Optimization of Anisotropic Diffusion Schedules
Pengxi Liu, Zeyu Michael Li, Xiang Cheng
We introduce a variational framework for diffusion models with anisotropic noise schedules parameterized by a matrix-valued path that allocates noise across subspaces. Cen…
cs.LG2024
Graph Transformers Dream of Electric Flow
Xiang Cheng, Lawrence Carin, Suvrit Sra
We show theoretically and empirically that the linear Transformer, when applied to graph data, can implement algorithms that solve canonical problems such as electric flow and eige…
math.OC2024
Riemannian Bilevel Optimization
Sanchayan Dutta, Xiang Cheng, Suvrit Sra
We develop new algorithms for Riemannian bilevel optimization. We focus in particular on batch and stochastic gradient-based methods, with the explicit goal of avoiding second-orde…