10 papers
Finding Koopman Invariant Subspaces via Personalized PageRank
Hyukpyo Hong, Qin Li, Matthew J. Colbrook +1
Selecting a finite dictionary of observables whose span is Koopman-invariant is a central challenge in data-driven Koopman operator approximation. We address this problem by exploi…
Likelihood landscape of binary latent model on a tree
David Clancy, Hanbaek Lyu, Sebastien Roch
We investigate the optimization landscape of maximum likelihood estimation (MLE) for the Cavender-Farris-Neyman (CFN) model, a two-state latent tree model fundamental to statistica…
Scaling limit of Sinkhorn-rescaled Random Matrices via Stability of Static Schrödinger Bridges
Danny Duan, Hanbaek Lyu, William Powell
We analyze the asymptotic behavior and scaling limits of large random matrices rescaled via the Sinkhorn algorithm to match prescribed row and column margins. For a random matrix w…
Diffusive Scaling limit of stochastic Box-Ball systems and PushTASEP
David Keating, Minjun Kim, Eva Loeser +1
We introduce the Stochastic Box-Ball System (SBBS), a probabilistic cellular automaton that generalizes the classic Takahashi-Satsuma Box-Ball System. In SBBS, particles are transp…
Regularized Overestimated Newton
Danny Duan, Hanbaek Lyu
We propose Regularized Overestimated Newton (RON), a Newton-type method with low per-iteration cost and strong global and local convergence guarantees for smooth convex optimizatio…
Sobolev acceleration for neural networks
Jong Kwon Oh, Hanbaek Lyu, Hwijae Son
Sobolev training, which integrates target derivatives into the loss functions, has been shown to accelerate convergence and improve generalization compared to conventional tr…