From Tsallis to KL: Convergence and Error Estimates for Tsallis-Regularized Optimal Transport

@misc{suguro2026from,
  title = {{From Tsallis to KL: Convergence and Error Estimates for Tsallis-Regularized Optimal Transport}},
  author = {Takeshi Suguro and Toshiaki Yachimura},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.06432},
  eprint = {2609.06432},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.06432},
  note = {CC BY 4.0},
}

TY  - UNPB
TI  - From Tsallis to KL: Convergence and Error Estimates for Tsallis-Regularized Optimal Transport
AU  - Takeshi Suguro
AU  - Toshiaki Yachimura
PY  - 2026
DA  - 2026/09/06
PB  - arXiv
DO  - 10.48550/arxiv.2609.06432
UR  - https://arxiv.org/abs/2609.06432
AB  - We study the Tsallis-to-Kullback--Leibler (KL) limit for entropy-regularized optimal transport with nonnegative bounded continuous costs. Fixing the regularization parameter ε > 0, we first derive an exact variational reformulation of Tsallis-regularized optimal transport in terms of the Tsallis information projection onto the set of couplings. The formula isolates an explicit correction term and thereby explains why, unlike in the KL case, the regularized transport problem and the corresponding information projection problem do not coincide exactly. We also establish existence and uniqueness for the Tsallis information projection. We then prove, with respect to the narrow topology, the Γ-convergence of the Tsallis-regularized functionals to the KL-regularized functional as q↓1, together with narrow convergence of their unique minimizers. Finally, we obtain explicit error estimates of order O(q−1) for both the regularized optimal transport values and the associated information projection values. These results quantify the passage from Tsallis regularization to the classical KL setting and clarify the relation between entropic regularization and information projection for 1 < q ≤ 2.
ER  -