| 2025 | AISTATS | Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits. | Nicolas Nguyen, Imad Aouali, Andrs Gyrgy, Claire Vernade |
| 2025 | ICLR | Toward Understanding In-context vs. In-weight Learning. | Bryan Chan, Xinyi Chen, Andrs Gyrgy, Dale Schuurmans |
| 2025 | ICLR | Learning Continually by Spectral Regularization. | Alex Lewandowski, Michal Bortkiewicz, Saurabh Kumar, Andrs Gyrgy, Dale Schuurmans, Mateusz Ostaszewski, Marlos C. Machado |
| 2025 | WWW | A Scalable Crawling Algorithm Utilizing Noisy Change-Indicating Signals. | Julian Zimmert, Rbert Busa-Fekete, Andrs Gyrgy, Linhai Qiu, Hyomin Choi, Tzu-Wei Sung, Hao Shen, Sharmila Subramaniam, Li Xiao |
| 2023 | COLT | A Second-Order Method for Stochastic Bandit Convex Optimisation. | Tor Lattimore, Andrs Gyrgy |
| 2023 | ICML | Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost. | Sanae Amani, Tor Lattimore, Andrs Gyrgy, Lin Yang |
| 2023 | ICML | Understanding Self-Predictive Learning for Reinforcement Learning. | Yunhao Tang, Zhaohan Daniel Guo, Pierre Harvey Richemond, Bernardo vila Pires, Yash Chandak, Rmi Munos, Mark Rowland, Mohammad Gheshlaghi Azar, Charline Le Lan, Clare Lyle, Andrs Gyrgy, Shantanu Thakoor, Will Dabney, Bilal Piot, Daniele Calandriello, Michal Valko |
| 2022 | AISTATS | Faster Rates, Adaptive Algorithms, and Finite-Time Bounds for Linear Composition Optimization and Gradient TD Learning. | Anant Raj, Pooria Joulani, Andrs Gyrgy, Csaba Szepesvri |
| 2022 | ALT | TensorPlan and the Few Actions Lower Bound for Planning in MDPs under Linear Realizability of Optimal Value Functions. | Gellrt Weisz, Csaba Szepesvri, Andrs Gyrgy |
| 2022 | ICLR | Defending Against Image Corruptions Through Adversarial Augmentations. | Dan Andrei Calian, Florian Stimberg, Olivia Wiles, Sylvestre-Alvise Rebuffi, Andrs Gyrgy, Timothy A. Mann, Sven Gowal |
| 2022 | ICLR | On the Role of Neural Collapse in Transfer Learning. | Tomer Galanti, Andrs Gyrgy, Marcus Hutter |
| 2021 | AISTATS | Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting. | Ilja Kuzborskij, Claire Vernade, Andrs Gyrgy, Csaba Szepesvri |
| 2021 | COLT | Improved Regret for Zeroth-Order Stochastic Convex Bandits. | Tor Lattimore, Andrs Gyrgy |
| 2021 | COLT | Mirror Descent and the Information Ratio. | Tor Lattimore, Andrs Gyrgy |
| 2021 | ICML | Adapting to Delays and Data in Adversarial Multi-Armed Bandits. | Andrs Gyrgy, Pooria Joulani |
| 2020 | ICLR | A Framework for robustness Certification of Smoothed Classifiers using F-Divergences. | Krishnamurthy (Dj) Dvijotham, Jamie Hayes, Borja Balle, J. Zico Kolter, Chongli Qin, Andrs Gyrgy, Kai Xiao, Sven Gowal, Pushmeet Kohli |
| 2020 | ICML | A simpler approach to accelerated optimization: iterative averaging meets optimism. | Pooria Joulani, Anant Raj, Andrs Gyrgy, Csaba Szepesvri |
| 2020 | ICML | Non-Stationary Delayed Bandits with Intermediate Observations. | Claire Vernade, Andrs Gyrgy, Timothy A. Mann |
| 2020 | ICSE | Minimal Assumptions Refinement for Realizable Specifications. | Davide G. Cavezza, Dalal Alrajeh, Andrs Gyrgy |
| 2019 | AIES | Degenerate Feedback Loops in Recommender Systems. | Ray Jiang, Silvia Chiappa, Tor Lattimore, Andrs Gyrgy, Pushmeet Kohli |
| 2019 | AISTATS | Adaptive MCMC via Combining Local Samplers. | Kirash Shaloudegi, Andrs Gyrgy |
| 2019 | ICML | Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems. | Timothy A. Mann, Sven Gowal, Andrs Gyrgy, Huiyi Hu, Ray Jiang, Balaji Lakshminarayanan, Prav Srinivasan |
| 2019 | ICML | CapsAndRuns: An Improved Method for Approximately Optimal Algorithm Configuration. | Gellrt Weisz, Andrs Gyrgy, Csaba Szepesvri |
| 2019 | INFOCOM | Reinforcement Learning to Minimize Age of Information with an Energy Harvesting Sensor with HARQ and Sensing Cost. | Elif Tuge Ceran, Deniz Gndz, Andrs Gyrgy |
| 2018 | FM | A Weakness Measure for GR(1) Formulae. | Davide Giacomo Cavezza, Dalal Alrajeh, Andrs Gyrgy |
| 2018 | ICML | LEAPSANDBOUNDS: A Method for Approximately Optimal Algorithm Configuration. | Gellrt Weisz, Andrs Gyrgy, Csaba Szepesvri |
| 2018 | PIMRC | A Reinforcement Learning Approach to Age of Information in Multi-User Networks. | Elif Tugce Ceran, Deniz Gndz, Andrs Gyrgy |
| 2018 | WCNC | Average age of information with hybrid ARQ under a resource constraint. | Elif Tugce Ceran, Deniz Gndz, Andrs Gyrgy |
| 2017 | ALT | A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism, Composite Objectives, and Variational Bounds. | Pooria Joulani, Andrs Gyrgy, Csaba Szepesvri |
| 2017 | WiOpt | Energy-efficient wireless content delivery with proactive caching. | Samuel O. Somuyiwa, Andrs Gyrgy, Deniz Gndz |
| 2017 | WiOpt | Improved policy representation and policy search for proactive content caching in wireless networks. | Samuel O. Somuyiwa, Andrs Gyrgy, Deniz Gndz |
| 2016 | AAAI | Delay-Tolerant Online Convex Optimization: Unified Analysis and Adaptive-Gradient Algorithms. | Pooria Joulani, Andrs Gyrgy, Csaba Szepesvri |
| 2016 | AISTATS | (Bandit) Convex Optimization with Biased Noisy Gradient Oracles. | Xiaowei Hu, Prashanth L. A., Andrs Gyrgy, Csaba Szepesvri |
| 2016 | ICML | Shifting Regret, Mirror Descent, and Matrices. | Andrs Gyrgy, Csaba Szepesvri |
| 2015 | AISTATS | Near-optimal max-affine estimators for convex regression. | Gbor Balzs, Andrs Gyrgy, Csaba Szepesvri |
| 2015 | AISTATS | Exploiting Symmetries to Construct Efficient MCMC Algorithms With an Application to SLAM. | Roshan Shariff, Andrs Gyrgy, Csaba Szepesvri |
| 2015 | ICML | Deterministic Independent Component Analysis. | Ruitong Huang, Andrs Gyrgy, Csaba Szepesvri |
| 2015 | ICML | On Identifying Good Options under Combinatorially Structured Feedback in Finite Noisy Environments. | Yifan Wu, Andrs Gyrgy, Csaba Szepesvri |
| 2015 | IJCAI | Fast Cross-Validation for Incremental Learning. | Pooria Joulani, Andrs Gyrgy, Csaba Szepesvri |
| 2014 | ALT | On Learning the Optimal Waiting Time. | Tor Lattimore, Andrs Gyrgy, Csaba Szepesvri |
| 2014 | ICML | Online Learning in Markov Decision Processes with Changing Cost Sequences. | Travis Dick, Andrs Gyrgy, Csaba Szepesvri |
| 2014 | ICML | Adaptive Monte Carlo via Bandit Allocation. | James Neufeld, Andrs Gyrgy, Csaba Szepesvri, Dale Schuurmans |
| 2013 | DCC | Partition Tree Weighting. | Joel Veness, Martha White, Michael Bowling, Andrs Gyrgy |
| 2013 | ICML | A Randomized Mirror Descent Algorithm for Large Scale Multiple Kernel Learning. | Arash Afkanpour, Andrs Gyrgy, Csaba Szepesvri, Michael Bowling |
| 2013 | ICML | Online Learning under Delayed Feedback. | Pooria Joulani, Andrs Gyrgy, Csaba Szepesvri |
| 2012 | ISIT | Efficient tracking of large classes of experts. | Andrs Gyrgy, Tams Linder, Gbor Lugosi |
| 2011 | ISIT | Near-optimal rates for limited-delay universal lossy source coding. | Andrs Gyrgy, Gergely Neu |
| 2010 | COLT | The Online Loop-free Stochastic Shortest-Path Problem. | Gergely Neu, Andrs Gyrgy, Csaba Szepesvri |
| 2009 | SACI | Soft computing control of Type 1 diabetes described at molecular levels. | Levente Kovcs, Andrs Gyrgy, Balzs Beny, Zoltn Beny, Adalbert Kovcs |
| 2008 | COLT | On-line Sequential Bin Packing. | Andrs Gyrgy, Gbor Lugosi, Gyrgy Ottucsk |
| 2007 | IJCAI | Continuous Time Associative Bandit Problems. | Andrs Gyrgy, Levente Kocsis, Ivett Szab, Csaba Szepesvri |
| 2006 | COLT | The Shortest Path Problem Under Partial Monitoring. | Andrs Gyrgy, Tams Linder, Gyrgy Ottucsk |
| 2006 | ITW | The Shortest Path Problem in the Bandit Setting. | Andrs Gyrgy, Tams Linder, Gbor Lugosi |
| 2005 | COLT | Tracking the Best of Many Experts. | Andrs Gyrgy, Tams Linder, Gbor Lugosi |
| 2005 | ISIT | Tracking the best quantizer. | Andrs Gyrgy, Tams Linder, Gbor Lugosi |
| 2004 | DCC | A "Follow the Perturbed Leader"-type Algorithm for Zero-Delay Quantization of Individual Sequence. | Andrs Gyrgy, Tams Linder, Gbor Lugosi |
| 2004 | ISIT | Improved convergence rates in empirical vector quantizer design. | Andrs Antos, Lszl Gyrfi, Andrs Gyrgy |
| 2004 | ISIT | Efficient algorithms and minimax bounds for zero-delay lossy source coding. | Andrs Gyrgy, Tams Linder, Gbor Lugosi |
| 2001 | GLOBECOM | Estimates on the packet loss ratio via queue tail probabilities. | Andrs Gyrgy, Tams Borsos |