| 2026 | COLT | On-Average Stability of Multipass Preconditioned SGD and Effective Dimension. | Simon Vary, Tyler Farghly, Ilja Kuzborskij, Patrick Rebeschini |
| 2024 | COLT | Better-than-KL PAC-Bayes Bounds. | Ilja Kuzborskij, Kwang-Sung Jun, Yulian Wu, Kyoungseok Jang, Francesco Orabona |
| 2023 | COLT | Tighter PAC-Bayes Bounds Through Coin-Betting. | Kyoungseok Jang, Kwang-Sung Jun, Ilja Kuzborskij, Francesco Orabona |
| 2021 | AISTATS | Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting. | Ilja Kuzborskij, Claire Vernade, Andrs Gyrgy, Csaba Szepesvri |
| 2021 | COLT | Nonparametric Regression with Shallow Overparameterized Neural Networks Trained by GD with Early Stopping. | Ilja Kuzborskij, Csaba Szepesvri |
| 2021 | ICML | A Distribution-dependent Analysis of Meta Learning. | Mikhail Konobeev, Ilja Kuzborskij, Csaba Szepesvri |
| 2019 | AISTATS | Efficient Linear Bandits through Matrix Sketching. | Ilja Kuzborskij, Leonardo Cella, Nicol Cesa-Bianchi |
| 2019 | COLT | Distribution-Dependent Analysis of Gibbs-ERM Principle. | Ilja Kuzborskij, Nicol Cesa-Bianchi, Csaba Szepesvri |
| 2018 | ICML | Data-Dependent Stability of Stochastic Gradient Descent. | Ilja Kuzborskij, Christoph H. Lampert |
| 2016 | CVPR | When Nave Bayes Nearest Neighbors Meet Convolutional Neural Networks. | Ilja Kuzborskij, Fabio Maria Carlucci, Barbara Caputo |
| 2015 | ICIAP | Transfer Learning Through Greedy Subset Selection. | Ilja Kuzborskij, Francesco Orabona, Barbara Caputo |
| 2013 | CVPR | From N to N+1: Multiclass Transfer Incremental Learning. | Ilja Kuzborskij, Francesco Orabona, Barbara Caputo |
| 2013 | ICML | Stability and Hypothesis Transfer Learning. | Ilja Kuzborskij, Francesco Orabona |