跳到正文
arXiv cs.AI· Ivan Jaen Marquez, Sotirios Panagiotis Chytas, Vikas Singh·· 4 小时前AI 评分20

ToR-OT:用自回归 token 回归学习最优传输方案

Learning Optimal Transport Plans Via Autoregressive Token Regression

AI 导读

ToR-OT 是一个基于 Transformer 的模型,将离散最优传输(OT)重构为结构化序列生成任务,通过自回归 token 回归直接解码稀疏传输方案,而非在测试时求解优化问题。

正文 · 原文

View PDF HTML (experimental)

Abstract:Optimal Transport (OT) provides a principled framework for finding the minimum cost coupling between probability distributions. Classical solvers remain the gold standard for this task. At the same time, OT is an ideal testbed for studying whether learning-based amortized models can internalize the structure of OT type problems. Here, ground-truth solutions are available and marginal constraints are explicitly defined. Also, exact discrete solutions have well-characterized sparsity. We describe ToR-OT, a transformer-based model that learns to predict discrete OT plans through autoregressive token regression. We reframe OT into a structured sequence generation task. ToR-OT decodes sparse transport plans as sequences instead of solving an optimization task at test time. We focus on three properties: (a) Zero-shot generalization: pretraining on a large synthetic corpus of OT instances allows a single model to generalize to unseen distribution pairs and heterogeneous cost metrics without retraining, (b) Sparse primal decoding: by exploiting the inherent sparsity in exact discrete OT solutions, the decoder predicts only nonzero entries (avoids dense coupling outputs), (c) Amortized inference: on low-dimensional discrete problems, ToR-OT gives accurate approximate plans and compares favorably with per-instance neural OT baselines. Overall, ToR-OT is not yet a replacement for classical solvers, but a step toward understanding how autoregressive transformers can learn structure of constrained optimization problems like OT.
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.22218 [cs.LG]
  (or arXiv:2611.22218v1 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2611.22218

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Sotirios Panagiotis Chytas [view email]
[v1] Tue, 17 Nov 2026 04:57:26 UTC (12,512 KB)

来源:arXiv cs.AI · arxiv.org