Ilija Bogunovic

• Postdoctoral Fellow
• External Website
• ilijab@ethz.ch
• CAB G 68
• +41 44 632 64 96
• My research focus is on machine learning algorithms that are theoretically well-founded, robust and practically applicable. I am particularly interested in problems in sequential decision making and topics such as bandits, Bayesian optimization, experimental design, and reinforcement learning.

---

Publications

2024

Group Robust Preference Optimization in Reward-free RLHF S. S. Ramesh, Y. Hu, I. Chaimalas, V. Mehta, P. G. Sessa, H. B. Ammar, I. Bogunovic In Proc. Neural Information Processing Systems (NeurIPS), 2024 [bibtex] [abstract] [pdf]

Safe Model-Based Multi-Agent Mean-Field Reinforcement Learning M. Jusup, B. Pásztor, T. Janik, K. Zhang, F. Corman, A. Krause, I. Bogunovic In Proc. International Conference on Autonomous Agents and Multiagent Systems (AAMAS), International Foundation for Autonomous Agents and Multiagent Systems, 2024 [bibtex] [abstract] [pdf]

Distributionally Robust Model-based Reinforcement Learning with Large State Spaces S. Sundhar Ramesh, P. Giuseppe Sessa, Y. Hu, A. Krause, I. Bogunovic In Proc. International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR, volume 238, 2024 [bibtex] [abstract] [pdf]

2023

Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning B. Pásztor, A. Krause, I. Bogunovic In Transactions on Machine Learning Research, 2023 [bibtex] [abstract] [pdf]

2022

A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits I. Bogunovic, Z. Li, A. Krause, J. Scarlett In Proc. Neural Information Processing Systems (NeurIPS), 2022 [bibtex] [abstract] [pdf]

Movement Penalized Bayesian Optimization with Application to Wind Energy Systems S. S. Ramesh, P. G. Sessa, A. Krause, I. Bogunovic In Proc. Neural Information Processing Systems (NeurIPS), 2022 [bibtex] [abstract] [pdf]

Graph Neural Network Bandits P. Kassraie, A. Krause, I. Bogunovic In Proc. Neural Information Processing Systems (NeurIPS), 2022 [bibtex] [abstract] [pdf]

2021

Misspecified Gaussian Process Bandit Optimization I. Bogunovic, A. Krause In Proc. Neural Information Processing Systems (NeurIPS), 2021 [bibtex] [abstract] [pdf]

Risk-averse Heteroscedastic Bayesian Optimization A. Makarova, I. Usmanova, I. Bogunovic, A. Krause In Proc. Neural Information Processing Systems (NeurIPS), 2021 [bibtex] [abstract] [pdf] [video]

Online Submodular Resource Allocation with Applications to Rebalancing Shared Mobility Systems P. G. Sessa, I. Bogunovic, A. Krause, M. Kamgarpour In Proc. International Conference on Machine Learning (ICML), 2021 [bibtex] [abstract] [pdf]

Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning S. Curi, I. Bogunovic, A. Krause In Proc. International Conference on Machine Learning (ICML), 2021 [bibtex] [abstract] [pdf] [long]

Stochastic Linear Bandits Robust to Adversarial Attacks I. Bogunovic, A. Losalka, A. Krause, J. Scarlett In Proc. International Conference on Artificial Intelligence and Statistics (AISTATS), 2021 [bibtex] [abstract] [pdf]

2020

Contextual Games: Multi-Agent Learning with Side Information P. G. Sessa, I. Bogunovic, A. Krause, M. Kamgarpour In Proc. Neural Information Processing Systems (NeurIPS), 2020 [bibtex] [abstract] [pdf]

Learning to Play Sequential Games versus Unknown Opponents P. G. Sessa, I. Bogunovic, M. Kamgarpour, A. Krause In Proc. Neural Information Processing Systems (NeurIPS), 2020 [bibtex] [abstract] [pdf]

Distributionally Robust Bayesian Optimization J. Kirschner, I. Bogunovic, S. Jegelka, A. Krause In Proc. International Conference on Artificial Intelligence and Statistics (AISTATS), 2020 [bibtex] [abstract] [pdf]

Corruption-Tolerant Gaussian Process Bandit Optimization I. Bogunovic, A. Krause, J. Scarlett In Proc. International Conference on Artificial Intelligence and Statistics (AISTATS), 2020 [bibtex] [abstract] [pdf]

Mixed Strategies for Robust Optimization of Unknown Objectives P. G. Sessa, I. Bogunovic, M. Kamgarpour, A. Krause In Proc. International Conference on Artificial Intelligence and Statistics (AISTATS), 2020 [bibtex] [abstract] [pdf]

2019

No-Regret Learning in Unknown Games with Correlated Payoffs P. G. Sessa, I. Bogunovic, M. Kamgarpour, A. Krause In Proc. Neural Information Processing Systems (NeurIPS), 2019 [bibtex] [abstract] [pdf]

Overlapping Multi-Bandit Best Arm Identification J. Scarlett, I. Bogunovic, V. Cevher In The 2019 IEEE International Symposium on Information Theory (ISIT), 2019 [bibtex] [abstract] [pdf]

2018

Adversarially Robust Optimization with Gaussian Processes I. Bogunovic, J. Scarlett, S. Jegelka, V. Cevher In Conference on Neural Information Processing Systems (NeurIPS), 2018 [bibtex] [abstract] [pdf]

High-Dimensional Bayesian Optimization via Additive Models with Overlapping Groups P. Rolland, J. Scarlett, I. Bogunovic, V. Cevher In International Conference on Artificial Intelligence and Statistics (AISTATS), 2018 [bibtex] [abstract] [pdf]

Robust Maximization of Non-Submodular Objectives I. Bogunovic, J. Zhao, V. Cevher In International Conference on Artificial Intelligence and Statistics (AISTATS), 2018 [bibtex] [abstract] [pdf]

2017

Streaming Robust Submodular Maximization: A Partitioned Thresholding Approach S. Mitrovi\’c, I. Bogunovic, A. Norouzi-Fard, J. M. Tarnawski, V. Cevher In Advances in Neural Information Processing Systems (NIPS), 2017 [bibtex] [abstract] [pdf]

A Distributed Algorithm for Partitioned Robust Submodular Maximization I. Bogunovic, S. Mitrovi\’c, J. Scarlett, V. Cevher In Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2017 IEEE 7th International Workshop on, 2017 [bibtex] [abstract] [pdf]

Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization J. Scarlett, I. Bogunovic, V. Cevher In International Conference on Learning Theory (COLT), 2017 [bibtex] [abstract] [pdf]

Robust Submodular Maximization: A Non-Uniform Partitioning Approach I. Bogunovic, S. Mitrovi\’c, J. Scarlett, V. Cevher In International Conference on Machine Learning (ICML), 2017 [bibtex] [abstract] [pdf]

2016

Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation I. Bogunovic, J. Scarlett, A. Krause, V. Cevher In Proc. Neural Information Processing Systems (NeurIPS), 2016 [bibtex] [abstract] [pdf] [long]

An efficient streaming algorithm for the submodular cover problem A. Norouzi-Fard, A. Bazzi, I. Bogunovic, M. El Halabi, Y. P. Hsieh, V. Cevher In Advances in Neural Information Processing Systems (NIPS), 2016 [bibtex] [abstract] [pdf]

Time-varying Gaussian process bandit optimization I. Bogunovic, J. Scarlett, V. Cevher In Artificial Intelligence and Statistics (AISTATS), 2016 [bibtex] [abstract] [pdf]

Learning-based compressive subsampling L. Baldassarre, Y. H. Li, J. Scarlett, B. Gözcü, I. Bogunovic, V. Cevher In IEEE Journal of Selected Topics in Signal Processing, IEEE, volume 10, 2016 [bibtex] [abstract] [pdf]

2015

Active learning of self-concordant like multi-index functions I. Bogunovic, V. Cevher, J. Haupt, J. Scarlett In Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, 2015 [bibtex] [abstract] [pdf]

2014

Near-Optimally Teaching the Crowd to Classify A. Singla, I. Bogunovic, G. Bartók, A. Karbasi, A. Krause In Proc. International Conference on Machine Learning (ICML), 2014 [bibtex] [abstract] [pdf] [long]