activity
20242026
collaborators

6 papers

cs.LG2026

Low-dimensional topology of deep neural networks

Junyu Ren, Lek-Heng Lim

We study layered models, including feedforward networks, ResNets, and transformers, by limiting each layer to a width of , i.e., as representation space. This…

math.PR2025

Eigen, singular, cosine-sine, and Autonne--Takagi vectors distributions of random matrix ensembles

Yihan Guo, Lek-Heng Lim

We show that some of the best-known matrix decompositions of some of the best-known random matrix ensembles give us the unique -invariant uniform distributions on some of the be…

math.OC2025

Stiefel optimization is NP-hard

Zehua Lai, Lek-Heng Lim, Tianyun Tang

We show that linearly constrained linear optimization over a Stiefel or Grassmann manifold is NP-hard in general. We show that the same is true for unconstrained quadratic optimiza…

math.AG2025

Pierce-Birkhoff conjecture is true for splines

Zehua Lai, Lek-Heng Lim

We prove the Pierce--Birkhoff conjecture for splines, i.e., continuous piecewise polynomials of degree in variables on a hyperplane partition of , can be writ…

math.OC2025

Euclidean distance degree in manifold optimization

Zehua Lai, Lek-Heng Lim, Ke Ye

We determine the Euclidean distance degrees of the three most common manifolds arising in manifold optimization: flag, Grassmann, and Stiefel manifolds. For the Grassmannian, we wi…

cs.AI2024

Attention is a smoothed cubic spline

Zehua Lai, Lek-Heng Lim, Yucong Liu

We highlight a perhaps important but hitherto unobserved insight: The attention module in a transformer is a smoothed cubic spline. Viewed in this manner, this mysterious but criti…