Selected Publications
Online Newton Method for Bandit Convex Optimisation.
H. Fokkema, D. van der Hoeven, T. Lattimore, J. Mayo. 2024.
H. Fokkema, D. van der Hoeven, T. Lattimore, J. Mayo. 2024.
High Probability Risk Bounds via Sequential Predictors.
D. van der Hoeven, N. Zhivotovskiy, Nicolò Cesa-Bianchi. 2023.
D. van der Hoeven, N. Zhivotovskiy, Nicolò Cesa-Bianchi. 2023.
Learning on the Edge: Online Learning with Stochastic Feedback Graphs.
E. Esposito, F. Fusco, D van der Hoeven, and Nicolò Cesa-Bianchi. NeurIPS 2022.
E. Esposito, F. Fusco, D van der Hoeven, and Nicolò Cesa-Bianchi. NeurIPS 2022.
Nonstochastic Bandits and Experts with Arm-Dependent Delays.
D. van der Hoeven and Nicolò Cesa-Bianchi. Oral presentation at AISTATS 2022.
D. van der Hoeven and Nicolò Cesa-Bianchi. Oral presentation at AISTATS 2022.
Beyond Bandit Feedback in Online Multiclass Classification.
D. van der Hoeven, F. Fusco, and Nicolò Cesa-Bianchi. NeurIPS 2021 Sweater and Mug.
D. van der Hoeven, F. Fusco, and Nicolò Cesa-Bianchi. NeurIPS 2021 Sweater and Mug.
Exploiting the Surrogate Gap in Online Multiclass Classification.
D. van der Hoeven. NeurIPS 2020. Poster. Presentation. Mug.
D. van der Hoeven. NeurIPS 2020. Poster. Presentation. Mug.
User-Specified Local Differential Privacy in Unconstrained Adaptive Online Learning
D. van der Hoeven. NeurIPS 2019. Poster.
D. van der Hoeven. NeurIPS 2019. Poster.
The Many Faces of Exponential Weights in Online Learning
D. van der Hoeven, T. van Erven and W. Kotłowski. COLT 2018. Poster. Short presentation. Long presentation.
D. van der Hoeven, T. van Erven and W. Kotłowski. COLT 2018. Poster. Short presentation. Long presentation.