| Landscape Connectivity and Dropout Stability of SGD Solutions for Over-parameterized Neural Networks A Shevchenko, M Mondelli 37th International Conference on Machine Learning (ICML), 2019 | 52 | 2019 |
| Mean-field analysis of piecewise linear solutions for wide ReLU networks A Shevchenko, V Kungurtsev, M Mondelli Journal of Machine Learning Research 23 (130), 1-55, 2022 | 24 | 2022 |
| Fundamental limits of two-layer autoencoders, and achieving them with gradient methods A Shevchenko, K Kögler, H Hassani, M Mondelli International Conference on Machine Learning, 31151-31209, 2023 | 9 | 2023 |
| Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth K Kögler, A Shevchenko, H Hassani, M Mondelli 41th International Conference on Machine Learning (ICML), 2024 | 7 | 2024 |
| Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models J Hübotter, P Wolf, A Shevchenko, D Jüni, A Krause, G Kur arXiv preprint arXiv:2509.24510, 2025 | | 2025 |
| Attention with Trained Embeddings Provably Selects Important Tokens D Wu, A Shevchenko, S Oymak, M Mondelli NeurIPS 2025, 2025 | | 2025 |
| High-dimensional limits in artificial neural networks A Shevchenko | | 2024 |
| Scaling Matters in Deep Structured-Prediction Models A Shevchenko, A Osokin arXiv preprint arXiv:1902.11088, 2019 | | 2019 |
Marco MondelliProfessor, IST AustriaVerified email at ist.ac.at
