Preprints and submissions

  1. Baptista, R.*, Pooladian, A-A.*, Brennan, M., Marzouk Y., and Niles-Weed, J. (Joint first author) “Conditional simulation via entropic optimal transport: Toward non-parametric estimation of conditional Brenier maps” [arXiv] [PDF]
  2. Haviv, D.*, Pooladian, A-A.*, Pe’er, D., and Amos, B. (Joint first author) “Wasserstein Flow Matching: Generative modeling over families of distributions” [arXiv] [PDF]
  3. Pooladian, A-A., and Niles-Weed, J. “Plug-in estimation of Schrödinger bridges” [arXiv] [PDF]
  4. Divol, V., Niles-Weed, J., and Pooladian, A-A. (alphabetical) “Tight stability for entropic Brenier maps” [arXiv] [PDF]
  5. Pooladian, A-A., and Niles-Weed, J. “Entropic estimation of optimal transport maps” (2021) [arXiv] [PDF]

Conference papers

  1. Kassraie, P., Pooladian, A-A., Klein, M., Thornton, J., Niles-Weed, J., and Cuturi, M. “Progressive Entropic Optimal Transport Solvers”, in the 38th Conference on Neural Information Processing Systems (NeurIPS 2024). [arXiv] [PDF]
  2. Klein, M., Pooladian, A-A., Ablin, P., Ndiaye, E., Niles-Weed, J., and Cuturi, M. “Learning Costs for Structured Monge Displacements”, in the 38th Conference on Neural Information Processing Systems (NeurIPS 2024). [arXiv] [PDF]
  3. Jiang, Y., Chewi, S., and Pooladian, A-A. (Supervisory role) “Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein space”, in the 37th Conference on Learning Theory (COLT 2024) [Extended abstract]. [arXiv] [PDF] [Slides]
  4. Pooladian, A-A., Domingo-Enrich, C., Chen R., and Amos, B. “Neural Optimal Transport with Lagrangian Costs”, in the 40th International Conference on Uncertainty in Artificial Intelligence (UAI 2024). [PDF]
  5. Pooladian, A-A.*, Divol, V.*, and Niles-Weed, J. (Joint first author) “Minimax estimation of discontinuous optimal transport maps: The semi-discrete case”, in the 40th International Conference on Machine Learning (ICML 2023). [arXiv] [PDF] [Slides]
  6. Pooladian, A-A.*, Ben-Hamu, H.*, Domingo-Enrich, C.*, Amos, B., Lipman, Y., and Chen, R. (Joint first author) “Multisample Flow Matching: Straightening Flows with Minibatch Couplings”, in the 40th International Conference on Machine Learning (ICML 2023). [arXiv] [PDF]
  7. Pooladian, A-A., Cuturi, M., and Niles-Weed, J. “Debiaser Beware: Pitfalls of Centering Regularized Transport maps”, in the 39th International Conference on Machine Learning (ICML 2022). [arXiv] [PDF] [Slides]

Journal articles

  1. Divol, V., Niles-Weed, J., and Pooladian, A-A. (alphabetical) “Optimal transport map estimation in general function spaces”, to appear in Annals of Statistics (2025+) [arXiv] [PDF] [Slides]
  2. Chewi, S., and Pooladian, A-A. (alphabetical) “An entropic generalization of Caffarelli’s contraction theorem via covariance inequalities”, in Comptes Rendues Mathématique (2023) [arXiv] [PDF] [Slides]
  3. Domingo-Enrich, C., and Pooladian, A-A. (alphabetical) “An Explicit Expansion of the Kullback-Leibler Divergence along its Fisher-Rao gradient flow”, in Transactions on Machine Learning Research (2023) [arXiv] [PDF]

Workshop papers

  1. Pooladian, A-A., Domingo-Enrich, C., Chen R., and Amos, B. “Neural Optimal Transport with Lagrangian Costs” (2023), in New Frontiers in Learning, Control, and Dynamical Systems (ICML 2023 workshop). [PDF]
  2. Pooladian, A-A., and Niles-Weed, J. “Entropic estimation of optimal transport maps” (2021), in Optimal Transport and Machine Learning (NeurIPS 2021 workshop), with contributing talk and Best Paper Award. [arXiv] [PDF]
  3. Finlay, C., Gerolin, A., Oberman, A., Pooladian A-A. (alphabetical) “Learning normalizing flows from Entropy-Kantorovich potentials”, in Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models (ICML 2020 workshop), with contributing talk. [arXiv] [PDF]

pre-PhD conference and journal papers

  1. Hoheisel, T., Pablos, B., Pooladian, A-A., Schwartz, A., and Steverango, L. (alphabetical) “A study of one-parameter regularizations for mathematical programs with vanishing constraints”, in Optimization Methods and Software (2020). [arXiv] [PDF]
  2. Pooladian, A-A., Finlay, C., Hoheisel, T., and Oberman, A. “A principled approach for generating adversarial images under non-smooth dissimilarity metrics”, in 23rd International Conference on Artificial Intelligence and Statistics (AISTATS 2020). [arXiv] [PDF]
  3. Finaly C., Pooladian, A-A., and Oberman, A., “ The LogBarrier Adversarial Attack: Making effective use of decision boundary information”, in IEEE International Conference on Computer Vision (ICCV 2019). [arXiv] [PDF]