Embedded Files
Welcome to my homepage!
I am an Assistant Professor in the Department of Intelligent Systems, Delft University of Technology. Previously, I did a postdoc at the Mathematics Department at VU Amsterdam. I obtained my PhD at Universitat Pompeu Fabra, where I was advised by Gergely Neu and Gábor Lugosi.
I am working on designing and analyzing algorithms for sequential decision-making problems, with my primary focus on bandit problems and theoretical reinforcement learning.
Here you can find my CV, Google Scholar.
E-mail: julia.olkhovskaya@gmail.com .
Publications:
Publications:
Tim van Erven, Jack Mayo, Julia Olkhovskaya, Chen-Yu Wei: "An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction", NeurIPS 2025.
Dirk van der Hoeven, Julia Olkhovskaya, Tim van Erven: "Nearly Minimax Discrete Distribution Estimation in Kullback-Leibler Divergence with High Probability", ALT 2026.
Hamish Flynn, Julia Olkhovskaya, Paul Rognon-Vael: "Sparse Nonparametric Contextual Bandits", ALT 2026.
Nicolò Cesa-Bianchi, Khaled Eldowa, Emmanuel Esposito, Julia Olkhovskaya: "Improved Regret Bounds for Bandits with Expert Advice ", Journal of Artificial Intelligence Research, 2025.
Sattar Vakili, Julia Olkhovskaya: "Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm", NeurIPS 2024.
Gergely Neu, Julia Olkhovskaya, Sattar Vakili: "Adversarial Contextual Bandits Go Kernelized", ALT 2024.
Sattar Vakili, Julia Olkhovskaya: "Kernelized Reinforcement Learning with Order Optimal Regret Bounds", NeurIPS 2023. *
Julia Olkhovskaya, Jack Mayo, Tim van Erven, Gergely Neu, Chen-Yu Wei: "First- and Second-Order Bounds for Adversarial Linear Contextual Bandits", NeurIPS 2023.
Gabor Lugosi, Gergely Neu and Julia Olkhovskaya: "Learning to maximize global influence from local observations", under review.
Gergely Neu, Julia Olkhovskaya, Matteo Papini, Ludovic Schwartz: "Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits", NeurIPS 2022.
Gergely Neu and Julia Olkhovskaya: “Online learning in MDPs with linear function approximation and bandit feedback”, NeurIPS 2021.
Gergely Neu and Julia Olkhovskaya: “Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits”, COLT 2020.
Gabor Lugosi, Gergely Neu and Julia Olkhovskaya: “Online influence maximization with local observations”, ALT 2019
Page updated
Google Sites
Report abuse