Aram-Alexandre Pooladian

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 17

Top Topics

Variational Inference

Top Venues

Publications

Yiheng Jiang, Sinho Chewi, Aram-Alexandre Pooladian
Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein space. COLT (2024)
Aram-Alexandre Pooladian, Carles Domingo-Enrich, Ricky T. Q. Chen, Brandon Amos
Neural Optimal Transport with Lagrangian Costs. CoRR (2024)
Parnian Kassraie, Aram-Alexandre Pooladian, Michal Klein, James Thornton, Jonathan Niles-Weed, Marco Cuturi
Progressive Entropic Optimal Transport Solvers. CoRR (2024)
Aram-Alexandre Pooladian, Heli Ben-Hamu, Carles Domingo-Enrich, Brandon Amos, Yaron Lipman, Ricky T. Q. Chen
Multisample Flow Matching: Straightening Flows with Minibatch Couplings. CoRR (2023)
Aram-Alexandre Pooladian, Heli Ben-Hamu, Carles Domingo-Enrich, Brandon Amos, Yaron Lipman, Ricky T. Q. Chen
Multisample Flow Matching: Straightening Flows with Minibatch Couplings. ICML (2023)
Aram-Alexandre Pooladian, Vincent Divol, Jonathan Niles-Weed
Minimax estimation of discontinuous optimal transport maps: The semi-discrete case. ICML (2023)
Michal Klein, Aram-Alexandre Pooladian, Pierre Ablin, Eugène Ndiaye, Jonathan Niles-Weed, Marco Cuturi
Learning Costs for Structured Monge Displacements. CoRR (2023)
Yiheng Jiang, Sinho Chewi, Aram-Alexandre Pooladian
Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein space. CoRR (2023)
Carles Domingo-Enrich, Aram-Alexandre Pooladian
An Explicit Expansion of the Kullback-Leibler Divergence along its Fisher-Rao Gradient Flow. Trans. Mach. Learn. Res. 2023 (2023)
Aram-Alexandre Pooladian, Marco Cuturi, Jonathan Niles-Weed
Debiaser Beware: Pitfalls of Centering Regularized Transport Maps. ICML (2022)
Tim Hoheisel, Blanca Pablos, Aram-Alexandre Pooladian, Alexandra Schwartz, Luke Steverango
A study of one-parameter regularization methods for mathematical programs with vanishing constraints. Optim. Methods Softw. 37 (2) (2022)
Aram-Alexandre Pooladian, Chris Finlay, Tim Hoheisel, Adam M. Oberman
A principled approach for generating adversarial images under non-smooth dissimilarity metrics. AISTATS (2020)
Chris Finlay, Augusto Gerolin, Adam M. Oberman, Aram-Alexandre Pooladian
Learning normalizing flows from Entropy-Kantorovich potentials. CoRR (2020)
Chris Finlay, Aram-Alexandre Pooladian, Adam M. Oberman
The LogBarrier Adversarial Attack: Making Effective Use of Decision Boundary Information. ICCV (2019)
Aram-Alexandre Pooladian, Chris Finlay, Adam M. Oberman
Farkas layers: don't shift the data, fix the geometry. CoRR (2019)
Chris Finlay, Aram-Alexandre Pooladian, Adam M. Oberman
The LogBarrier adversarial attack: making effective use of decision boundary information. CoRR (2019)
Aram-Alexandre Pooladian, Chris Finlay, Tim Hoheisel, Adam M. Oberman
A principled approach for generating adversarial images under non-smooth dissimilarity metrics. CoRR (2019)