| The Universal Approximation Property A Kratsios Annals of Mathematics and Artificial Intelligence, 2021 | 140* | 2021 |
| Non-Euclidean Universal Approximation A Kratsios, E Bilokopytov Advances in Neural Information Processing Systems 33, 10635--10646, 2020 | 92 | 2020 |
| Universal Approximation Theorems for Differentiable Geometric Deep Learning A Kratsios, L Papon Journal of Machine Learning Research 23 (196), 1-73, 2022 | 79 | 2022 |
| Out-of-distributional risk bounds for neural operators with applications to the Helmholtz equation JAL Benitez, T Furuya, F Faucher, A Kratsios, X Tricoche, MV de Hoop Journal of Computational Physics, 113168, 2024 | 53* | 2024 |
| Designing Universal Causal Deep Learning Models: The Geometric (Hyper) Transformer B Acciaio, A Kratsios, G Pammer Mathematical Finance, 2023 | 52* | 2023 |
| Universal Approximation Under Constraints is Possible with Transformers A Kratsios, B Zamanlooy, I Dokmanić, T Liu International Conference on Learning Representations (ICLR) 10, 2022 | 47 | 2022 |
| Neu: A Meta-Algorithm for Universal UAP-Invariant Feature Representation A Kratsios, C Hyndman The Journal of Machine Learning Research 22 (1), 4102-4152, 2021 | 42 | 2021 |
| Instance-dependent generalization bounds via optimal transport S Hou, P Kassraie, A Kratsios, A Krause, J Rothfuss Journal of Machine Learning Research, 2023 | 23 | 2023 |
| Small Transformers Compute Universal Metric Embeddings A Kratsios, V Debarnot, I Dokmanić Journal of Machine Learning Research (JMLR), 2023 | 22 | 2023 |
| Deep arbitrage-free learning in a generalized HJM framework via arbitrage-regularization A Kratsios, C Hyndman Risks 8 (2), 40, 2020 | 22* | 2020 |
| Characterizing overfitting in kernel ridgeless regression through the eigenspectrum TS Cheng, A Lucchi, A Kratsios, D Belius arXiv preprint arXiv:2402.01297, 2024 | 21 | 2024 |
| Designing universal causal deep learning models: The case of infinite-dimensional dynamical systems from stochastic analysis L Galimberti, A Kratsios, G Livieri arXiv preprint arXiv:2210.13300, 2022 | 20 | 2022 |
| Denise: Deep Robust Principal Component Analysis for Positive Semidefinite Matrices JT C Herrera, F Krach, A Kratsios, P Ruyssen Transactions on Machine Learning Research (TMLR), 2023 | 16* | 2023 |
| A theoretical analysis of the test error of finite-rank kernel ridge regression TS Cheng, A Lucchi, A Kratsios, I Dokmanić, D Belius Advances in Neural Information Processing Systems 36, 4767-4798, 2023 | 15 | 2023 |
| Universal Regular Conditional Distributions via Probabilistic Transformers A Kratsios Constructive Approximation 57 (3), 1145-1212, 2023 | 15* | 2023 |
| Bridging the gap between approximation and learning via optimal approximation by relu mlps of maximal regularity R Hong, A Kratsios arXiv preprint arXiv:2409.12335, 2024 | 13 | 2024 |
| Mixture of experts soften the curse of dimensionality in operator learning A Kratsios, T Furuya, JAL Benitez, M Lassas, M de Hoop arXiv preprint arXiv:2404.09101, 2024 | 11 | 2024 |
| Do ReLU Networks Have An Edge When Approximating Compactly-Supported Functions? A Kratsios, B Zamanlooy Transactions on Machine Learning Research 1 (1), 1-21, 2022 | 11* | 2022 |
| Learning Sub-Patterns in Piece-Wise Continuous Functions A Kratsios, B Zamanlooy Neurocomputing 480 (10.1016/j.neucom.2022.01), 192-211, 2022 | 11 | 2022 |
| Neural snowflakes: Universal latent graph inference via trainable latent geometries HSO Borde, A Kratsios arXiv preprint arXiv:2310.15003, 2023 | 7* | 2023 |
Ivan DokmanićAssociate Professor, Department of Mathematics and Computer Science, University of BaselVerified email at illinois.edu
