Learning of Population Dynamics: Inverse Optimization Meets JKO Scheme

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Persiianov, Mikhail, Chen, Jiawei, Mokrov, Petr, Tyurin, Alexander, Burnaev, Evgeny, Korotin, Alexander
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915829348564992
author Persiianov, Mikhail
Chen, Jiawei
Mokrov, Petr
Tyurin, Alexander
Burnaev, Evgeny
Korotin, Alexander
author_facet Persiianov, Mikhail
Chen, Jiawei
Mokrov, Petr
Tyurin, Alexander
Burnaev, Evgeny
Korotin, Alexander
contents Learning population dynamics involves recovering the underlying process that governs particle evolution, given evolutionary snapshots of samples at discrete time points. Recent methods frame this as an energy minimization problem in probability space and leverage the celebrated JKO scheme for efficient time discretization. In this work, we introduce $\texttt{iJKOnet}$, an approach that combines the JKO framework with inverse optimization techniques to learn population dynamics. Our method relies on a conventional $\textit{end-to-end}$ adversarial training procedure and does not require restrictive architectural choices, e.g., input-convex neural networks. We establish theoretical guarantees for our methodology and demonstrate improved performance over prior JKO-based methods. The code of $\texttt{iJKOnet}$ is available at https://github.com/MuXauJl11110/iJKOnet.
format Preprint
id arxiv_https___arxiv_org_abs_2506_01502
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning of Population Dynamics: Inverse Optimization Meets JKO Scheme
Persiianov, Mikhail
Chen, Jiawei
Mokrov, Petr
Tyurin, Alexander
Burnaev, Evgeny
Korotin, Alexander
Machine Learning
Artificial Intelligence
Learning population dynamics involves recovering the underlying process that governs particle evolution, given evolutionary snapshots of samples at discrete time points. Recent methods frame this as an energy minimization problem in probability space and leverage the celebrated JKO scheme for efficient time discretization. In this work, we introduce $\texttt{iJKOnet}$, an approach that combines the JKO framework with inverse optimization techniques to learn population dynamics. Our method relies on a conventional $\textit{end-to-end}$ adversarial training procedure and does not require restrictive architectural choices, e.g., input-convex neural networks. We establish theoretical guarantees for our methodology and demonstrate improved performance over prior JKO-based methods. The code of $\texttt{iJKOnet}$ is available at https://github.com/MuXauJl11110/iJKOnet.
title Learning of Population Dynamics: Inverse Optimization Meets JKO Scheme
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.01502