Student Reports

Report 1

Learning static neural optimal transport maps and couplings—covering balanced strong OT, weak OT, and unbalanced OT—via scalable primal/dual and generative (GAN-style) formulations.

Table 1
№ Article Conference Links Status
1 Large scale optimal transport and mapping estimation ICLR 2018 arXiv, OpenReview Ilia Stepanov
2 Three-Player Wasserstein GAN via Amortised Duality IJCAI 2019 IJCAI Fedor Sobolevsky
3 Scalable Unbalanced Optimal Transport using Generative Adversarial Networks ICLR 2019 arXiv, OpenReview Altay Eynullayev
4 Optimal transport mapping via input convex neural networks ICML 2020 arXiv Denis Rubtsov
5 Kantorovich Strikes Back! Wasserstein GANs are not Optimal Transport? NeurIPS 2022 arXiv, OpenReview Dmitry Vasilenko
6 Neural Optimal Transport ICLR 2023 arXiv, OpenReview Ivan Papai

Note: the Neural Optimal Transport report should also cover Weak OT.

Report 2

Table 2
№ Article Conference Links Status
1 Solving Schrödinger Bridges via Maximum Likelihood Entropy (journal), 2021 arXiv Available
2 Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling NeurIPS 2021 arXiv Vladislav Minashkin
3 Score-based Generative Neural Networks for Large-Scale Optimal Transport NeurIPS 2021 arXiv Gleb Karpeev
4 Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory ICLR 2022 arXiv Vadim Kasiuk
5 Unpaired Image-to-Image Translation via Neural Schrödinger Bridge ICLR 2024 arXiv Vladislav Meshkov

Report 3

Table 3
№ Article Conference Links Status
1 I2SB: Image-to-Image Schrödinger Bridge ICML 2023 arXiv Muhammadsharif Nabiev
2 Simulation-Free Schrödinger Bridges via Score and Flow Matching AISTATS 2024 arXiv Available
3 Light and Optimal Schrödinger Bridge Matching ICML 2024 arXiv Available
4 Adversarial Schrödinger Bridge Matching NeurIPS 2024 arXiv Available
5 Optimal Flow Matching: Learning Straight Trajectories in Just One Step NeurIPS 2024 arXiv Available
Back to top