| Some theoretical properties of GANs G Biau, B Cadre, M Sangnier, U Tanielian | 57 | 2020 |
| Distributionally robust counterfactual risk minimization L Faury, U Tanielian, E Dohmatob, E Smirnova, F Vasile Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 3850-3857, 2020 | 52 | 2020 |
| Some theoretical insights into Wasserstein GANs GÊ Biau, M Sangnier, U Tanielian Journal of Machine Learning Research 22 (119), 1-45, 2021 | 51 | 2021 |
| Learning disconnected manifolds: a no GANs land U Tanielian, T Issenhuth, E Dohmatob, J Mary Proceedings of the 37 th International Conference on Machine Learning …, 2020 | 40 | 2020 |
| Approximating Lipschitz continuous functions with GroupSort neural networks U Tanielian, G Biau International Conference on Artificial Intelligence and Statistics, 442-450, 2021 | 38 | 2021 |
| Edibert, a generative model for image editing T Issenhuth, U Tanielian, J Mary, D Picard arXiv preprint arXiv:2111.15264, 2021 | 12 | 2021 |
| Relaxed softmax for PU learning U Tanielian, F Vasile Proceedings of the 13th ACM Conference on Recommender Systems, 119-127, 2019 | 12 | 2019 |
| Siamese cookie embedding networks for cross-device user matching U Tanielian, AM Tousch, F Vasile Companion Proceedings of the The Web Conference 2018, 85-86, 2018 | 11 | 2018 |
| Latent reweighting, an almost free improvement for GANs T Issenhuth, U Tanielian, D Picard, J Mary Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2022 | 6 | 2022 |
| AdBooster: Personalized Ad Creative Generation using Stable Diffusion Outpainting V Shilova, LD Santos, F Vasile, G Racic, U Tanielian arXiv preprint arXiv:2309.11507, 2023 | 5 | 2023 |
| Optimal 1-wasserstein distance for wgans A Stéphanovitch, U Tanielian, B Cadre, N Klutchnikoff, G Biau arXiv preprint arXiv:2201.02824, 2022 | 4 | 2022 |
| Unveiling the latent space geometry of push-forward generative models T Issenhuth, U Tanielian, J Mary, D Picard International Conference on Machine Learning, 14422-14444, 2023 | 3 | 2023 |
| Lessons from the AdKDD’21 privacy-preserving ML challenge E Diemert, R Fabre, A Gilotte, F Jia, B Leparmentier, J Mary, Z Qu, ... Proceedings of the ACM Web Conference 2022, 2026-2035, 2022 | 3 | 2022 |
| Wasserstein learning of determinantal point processes L Anquetil, M Gartrell, A Rakotomamonjy, U Tanielian, C Calauzènes arXiv preprint arXiv:2011.09712, 2020 | 2 | 2020 |
| Supplement to “Optimal 1-Wasserstein distance for WGANs.” A Stéphanovitch, U Tanielian, B Cadre, N Klutchnikoff, G Biau | 1 | 2024 |
| On the optimal precision of GANs T Issenhuth, U Tanielian, J Mary, D Picard | 1 | 2022 |
| Optimal 1-Wasserstein distance for WGANs A Stéphanovitch, U Tanielian, B Cadre, N Klutchnikoff, G Biau Bernoulli 30 (4), 2955-2978, 2024 | | 2024 |
| 3DGEN: A GAN-based approach for generating novel 3D models from image data A Schnepf, F Vasile, U Tanielian arXiv preprint arXiv:2312.08094, 2023 | | 2023 |
| What Users Want? WARHOL: A Generative Model for Recommendation J Samaran, U Tanielian, R Beaumont, F Vasile Recommender Systems in Fashion and Retail: Proceedings of the Third Workshop …, 2022 | | 2022 |
| What Users Want? WARHOL: A Generative Model for Recommendation UGO TANIELIAN, V FLAVIAN arXiv preprint arXiv:2109.01093, 2021 | | 2021 |
Gérard BiauProfessor, Sorbonne University, ParisVerified email at sorbonne-universite.fr
