Ilja Kuzborskij
Scholar

Ilja Kuzborskij

Google Scholar ID: 4Io_CtIAAAAJ
Google DeepMind
Machine LearningLearning Theory
Citations & Impact
All-time
Citations
1,336
 
H-index
18
 
i10-index
20
 
Publications
20
 
Co-authors
25
list available
Resume (English only)
Academic Achievements
  • 2025: Co-authored 'Pointwise confidence estimation in the non-linear ℓ²-regularized least squares' with Y. Abbasi-Yadkori (arXiv).
  • 2025: Co-authored 'Low-rank bias, weight decay, and model merging in neural networks' with Y. Abbasi-Yadkori (arXiv).
  • 2024: Co-authored 'Mitigating LLM Hallucinations via Conformal Abstention' (arXiv).
  • 2024: Paper 'To Believe or Not to Believe Your LLM' (with Cs. Szepesvári et al.) accepted at NeurIPS.
  • 2024: Paper 'Better-than-KL PAC-Bayes Bounds' (with K.-S. Jun et al.) accepted at COLT.
  • 2023: Paper 'Mixture Weight Estimation and Model Prediction in Multi-source Multi-target Domain Adaptation' (with Y. Deng and M. Mahdavi) accepted at NeurIPS.
  • 2022: Co-authored 'Learning Lipschitz Functions by GD-trained Shallow Overparameterized ReLU Neural Networks' with Cs. Szepesvári (arXiv).
  • 2019: Co-authored 'Efron-Stein PAC-Bayesian Inequalities' with Cs. Szepesvári (arXiv).