Alexander Y Tong — accepted AI-conference papers

2024

Simulation-Free Schrödinger Bridges via Score and Flow Matching

Alexander Y. Tong, Nikolay Malkin, Kilian Fatras, Lazar Atanackovic, Yanlei Zhang, Guillaume Huguet +2

AISTATS 2024poster

We present simulation-free score and flow matching ([SF]$^2$M), a simulation-free objective for inferring stochastic dynamics given unpaired samples drawn from arbitrary source and target distributions. Our method generalizes both the score-matching loss used in the training of diffusion models and…

Cited by 65 Source ↗PDF ↗code ↗Scholar ↗

2021

Diffusion Earth Mover’s Distance and Distribution Embeddings

Alexander Y Tong, Guillaume Huguet, Amine Natik, Kincaid Macdonald, Manik Kuchroo, Ronald Coifman +2

ICML 2021spotlight

We propose a new fast method of measuring distances between large numbers of related high dimensional datasets called the Diffusion Earth Mover’s Distance (EMD). We model the datasets as distributions supported on common data graph that is derived from the affinity matrix computed on the combined da…

Cited by 26 Source ↗PDF ↗code ↗Scholar ↗