works on
deep encoder depth 1dynamical system autoencoders 1feature augmentation 1lidar point cloud classification 1representation collapse 1

From the 1 of 5 linked papers with an AI index.

collaborators

5 papers

math.CO2026

A counterexample to the Albertson-Berman conjecture about induced forests in planar graphs

Mikhail Makarov

For a graph , denote by the number of vertices in the largest induced forest in . The Albertson-Berman conjecture, which had been open since 1979, states that $a(G) \g…

cs.LG2026

Depth-Dependent Hidden-State Collapse in Dynamical System Autoencoders for LiDAR Point-Cloud Classification

Patricia Medina, Hy P. G. Lam

The paper examines Dynamical System Autoencoders for LiDAR point‑cloud classification and discovers that increasing encoder depth to five layers causes a hidden‑state collapse, pro…

math.AP2026

Sampleability transport, nonlinear regularization, and the porous medium flow

Hy P. G. Lam

We study the Wasserstein projection of a compactly supported probability measure onto the class of measures whose density ratio is bounded, and we place this projection in a broade…

math.DG2026

Real Bers embedding on the line: Fisher-Rao linearization, Schwarzian curvature, and scattering coordinates

Hy Lam

We develop a real-analytic counterpart of the Bers embedding for the Fréchet Lie group $\Diff^{-\infty}(\R)$ of decay-controlled diffeomorphisms of the line, and establish its con…

math.DS2026

First variation of flat traces on negatively curved surfaces

Hy Lam

For a closed negatively curved surface the flat trace of the geodesic Koopman operators is the periodic orbit distribution \[ \mathrm{Tr}^{\flat} V_…