Hossein Zakerinia
Vienna, Austria
Hello! I am a Ph.D. student in Computer Science at Institute of Science and Technology Austria (ISTA), under the supervision of Prof. Christoph Lampert. Prior to ISTA, I received my B.Sc. in Computer Engineering at Sharif University of Technology.
I am interested in the theory and applications of machine learning. My research focuses on exploring learning paradigms beyond the conventional single-task i.i.d. data framework, including:
- Meta-Learning
- Lifelong Learning
- Continual Learning
I employ techniques derived from statistical learning theory, with a particular emphasis on PAC-Bayes, as well as online learning and optimization methods in my research.
news
| May 2026 | A new preprint From Privacy to Generalization: Linear Max-Information Bounds for DP-SGD is on arXiv. |
|---|---|
| May 2026 | Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions got accepted to ICML 2026. |
| Sep 2025 | Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes got accepted to NeurIPS 2025. |
| Jan 2025 | A new preprint From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learning is on arXiv. |
| May 2024 | More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms got accepted to ICML 2024. |