Preprints and submissions

  1. Pooladian, A-A., and Niles-Weed, J. “Entropic estimation of optimal transport maps” (2021) [PDF]

Conference papers

  1. 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). [Github] [PDF]
  2. 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) [Github] [PDF]

Workshop papers

  1. Finlay, C.*, Gerolin, A.*, Oberman, A., Pooladian A-A.* (alphabetical) “Learning normalizing flows from Entropy-Kantorovich potentials”, in ICML workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models (INNF+ 2020), with contributing talk, [PDF]

Journal articles

  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) [PDF]

Deep learning projects

  1. Pooladian, A-A.*, Finlay, C., and Oberman, A., “Farkas layers: Don’t shift the data, fix the geometry” (2019) [Github] [PDF]
  2. Pooladian, A-A.*, Iannantuono, A., Finlay, C., and Oberman, A., “A Langevin dynamics based approach to generating sparse adversarial perturbations” (2019) [PDF]
  3. Pooladian, A-A.*, Orfanides, G., “Sparse autoencoder using Scholtes relaxation scheme” (2018)

Fun projects

  1. Pooladian, A-A., “Batchwise projection algorithm onto total variation ball” (2019) [Github]