Dirk van der Hoeven

35 papers A* 13A 2B 1Journal 19
YearRankTypeTitle / Venue / Authors
2025 J jnl
A Unified Analysis of Nonstochastic Delayed Feedback for Combinatorial Semi-Bandits, Linear Bandits, and MDPs.
J. Mach. Learn. Res.
Lukas Zierahn, Dirk van der Hoeven, Tal Lancewicki, Aviv Rosenberg, Nicolò Cesa-Bianchi
2025 J jnl
Nearly Minimax Discrete Distribution Estimation in Kullback-Leibler Divergence with High Probability.
CoRR
Dirk van der Hoeven, Julia Olkhovskaia, Tim van Erven
2025 J jnl
When Lower-Order Terms Dominate: Adaptive Expert Algorithms for Heavy-Tailed Losses.
CoRR
Antoine Moulin, Emmanuel Esposito, Dirk van der Hoeven
2024 A* conf
Online Newton Method for Bandit Convex Optimisation Extended Abstract.
COLT
Hidde Fokkema, Dirk van der Hoeven, Tor Lattimore, Jack J. Mayo
2024 J jnl
Online Newton Method for Bandit Convex Optimisation.
CoRR
Hidde Fokkema, Dirk van der Hoeven, Tor Lattimore, Jack J. Mayo
2023 A* conf
A Unified Analysis of Nonstochastic Delayed Feedback for Combinatorial Semi-Bandits, Linear Bandits, and MDPs.
COLT
Dirk van der Hoeven, Lukas Zierahn, Tal Lancewicki, Aviv Rosenberg, Nicolò Cesa-Bianchi
2023 J jnl
A Unified Analysis of Nonstochastic Delayed Feedback for Combinatorial Semi-Bandits, Linear Bandits, and MDPs.
CoRR
Dirk van der Hoeven, Lukas Zierahn, Tal Lancewicki, Aviv Rosenberg, Nicolò Cesa-Bianchi
2023 A* conf
Delayed Bandits: When Do Intermediate Observations Help?
ICML
Emmanuel Esposito, Saeed Masoudian, Hao Qiu, Dirk van der Hoeven, Nicolò Cesa-Bianchi, Yevgeny Seldin
2023 J jnl
Delayed Bandits: When Do Intermediate Observations Help?
CoRR
Emmanuel Esposito, Saeed Masoudian, Hao Qiu, Dirk van der Hoeven, Nicolò Cesa-Bianchi, Yevgeny Seldin
2023 J jnl
High-Probability Risk Bounds via Sequential Predictors.
CoRR
Dirk van der Hoeven, Nikita Zhivotovskiy, Nicolò Cesa-Bianchi
2023 A conf
Nonstochastic Contextual Combinatorial Bandits.
AISTATS
Lukas Zierahn, Dirk van der Hoeven, Nicolò Cesa-Bianchi, Gergely Neu
2023 A* conf
Trading-Off Payments and Accuracy in Online Classification with Paid Stochastic Experts.
ICML
Dirk van der Hoeven, Ciara Pike-Burke, Hao Qiu, Nicolò Cesa-Bianchi
2023 J jnl
Trading-Off Payments and Accuracy in Online Classification with Paid Stochastic Experts.
CoRR
Dirk van der Hoeven, Ciara Pike-Burke, Hao Qiu, Nicolò Cesa-Bianchi
2022 A* conf
A Near-Optimal Best-of-Both-Worlds Algorithm for Online Learning with Feedback Graphs.
NeurIPS
Chloé Rouyer, Dirk van der Hoeven, Nicolò Cesa-Bianchi, Yevgeny Seldin
2022 J jnl
A Near-Optimal Best-of-Both-Worlds Algorithm for Online Learning with Feedback Graphs.
CoRR
Chloé Rouyer, Dirk van der Hoeven, Nicolò Cesa-Bianchi, Yevgeny Seldin
2022 A* conf
A Regret-Variance Trade-Off in Online Learning.
NeurIPS
Dirk van der Hoeven, Nikita Zhivotovskiy, Nicolò Cesa-Bianchi
2022 J jnl
A Regret-Variance Trade-Off in Online Learning.
CoRR
Dirk van der Hoeven, Nikita Zhivotovskiy, Nicolò Cesa-Bianchi
2022 B conf
Distributed Online Learning for Joint Regret with Communication Constraints.
ALT
Dirk van der Hoeven, Hédi Hadiji, Tim van Erven
2022 A* conf
Learning on the Edge: Online Learning with Stochastic Feedback Graphs.
NeurIPS
Emmanuel Esposito, Federico Fusco, Dirk van der Hoeven, Nicolò Cesa-Bianchi
2022 J jnl
Learning on the Edge: Online Learning with Stochastic Feedback Graphs.
CoRR
Emmanuel Esposito, Federico Fusco, Dirk van der Hoeven, Nicolò Cesa-Bianchi
2022 A conf
Nonstochastic Bandits and Experts with Arm-Dependent Delays.
AISTATS
Dirk van der Hoeven, Nicolò Cesa-Bianchi
2021 A* conf
Beyond Bandit Feedback in Online Multiclass Classification.
NeurIPS
Dirk van der Hoeven, Federico Fusco, Nicolò Cesa-Bianchi
2021 J jnl
Beyond Bandit Feedback in Online Multiclass Classification.
CoRR
Dirk van der Hoeven, Federico Fusco, Nicolò Cesa-Bianchi
2021 J jnl
Distributed Online Learning for Joint Regret with Communication Constraints.
CoRR
Dirk van der Hoeven, Hédi Hadiji, Tim van Erven
2021 J jnl
MetaGrad: Adaptation using Multiple Learning Rates in Online Learning.
CoRR
Tim van Erven, Wouter M. Koolen, Dirk van der Hoeven
2021 J jnl
MetaGrad: Adaptation using Multiple Learning Rates in Online Learning.
J. Mach. Learn. Res.
Tim van Erven, Wouter M. Koolen, Dirk van der Hoeven
2021 J jnl
Nonstochastic Bandits and Experts with Arm-Dependent Delays.
CoRR
Dirk van der Hoeven, Nicolò Cesa-Bianchi
2020 A* conf
Comparator-Adaptive Convex Bandits.
NeurIPS
Dirk van der Hoeven, Ashok Cutkosky, Haipeng Luo
2020 J jnl
Comparator-adaptive Convex Bandits.
CoRR
Dirk van der Hoeven, Ashok Cutkosky, Haipeng Luo
2020 A* conf
Exploiting the Surrogate Gap in Online Multiclass Classification.
NeurIPS
Dirk van der Hoeven
2020 J jnl
Exploiting the Surrogate Gap in Online Multiclass Classification.
CoRR
Dirk van der Hoeven
2020 A* conf
Open Problem: Fast and Optimal Online Portfolio Selection.
COLT
Tim van Erven, Dirk van der Hoeven, Wojciech Kotlowski, Wouter M. Koolen
2019 A* conf
User-Specified Local Differential Privacy in Unconstrained Adaptive Online Learning.
NeurIPS
Dirk van der Hoeven
2018 A* conf
The Many Faces of Exponential Weights in Online Learning.
COLT
Dirk van der Hoeven, Tim van Erven, Wojciech Kotlowski
2018 J jnl
The Many Faces of Exponential Weights in Online Learning.
CoRR
Dirk van der Hoeven, Tim van Erven, Wojciech Kotlowski