PUBLICATIONS OF ANDRÁS GYÖRGY

• P. Joulani, A. György, and Cs. Szepesvári, "Think out of the "Box": Generically-Constrained Asynchronous Composite Optimization and Hedging," Advances in Neural Information Processing Systems (NeurIPS 2019), Vancouver, BC, Canada, December 2019 (Pdf)

• R. Werpachowski, A. György, and Cs. Szepesvári, "Detecting Overfitting via Adversarial Examples," Advances in Neural Information Processing Systems (NeurIPS 2019), Vancouver, BC, Canada, December 2019. (Pdf)

• M. Z. Hameed, A. György, and D. Gündüz, "Communication without Interception: Defense against Modulation Detection," 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP 2019) -- Symposium: Machine Learning for Wireless Communications, Networking, and Security, Ottawa, ON, Canada, November 2019. (Pdf) Best paper award

• G. Weisz, A. György, and Cs. Szepesvári, "CapsAndRuns: An Improved Method for Approximately Optimal Algorithm Configuration," 36th International Conference on Machine Learning (ICML 2019), Long Beach, CA, USA, June 2019. (Pdf)

• T. A. Mann, S. Gowal, A. György, H. Hu, R. Jiang, B. Lakshminarayanan, and P. Srinivasan, "Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems," 36th International Conference on Machine Learning (ICML 2019), Long Beach, CA, USA, June 2019. (Pdf)

• K. Shaloudegi and A. György, "Adaptive MCMC via Combining Local Samplers," International Conference on Artificial Intelligence and Statistics (AISTATS 2019), Naha, Japan, April 2019. (Pdf, long version)

• E. Tugce Ceran, D. Gündüz, and A. György, "Reinforcement Learning to Minimize Age of Information with an Energy Harvesting Sensor with HARQ and Sensing Cost," IEEE Conference on Computer Communications Workshops (INFOCOM WORKSHOPS), April 2019. (Pdf)

• E. Tugce Ceran, D. Gündüz, and A. György, "Average Age of Information With Hybrid ARQ Under a Resource Constraint," IEEE Transactions on Wireless Communications, vol. 18 (3), pp. 1900-1913, March 2019. (Pdf)

• S. Somuyiwa, D. Gündüz, and A. György, "Multicast-Aware Proactive Caching in Wireless Networks with Deep Reinforcement Learning," IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), Cannes, France, July 2019.

• R. Jiang, S. Chiappa, T. Lattimore, A. György, and P. Kohli, "Degenerate Feedback Loops in Recommender Systems," 2nd AAAI/ACM Annual Conference on AI, Ethics, and Society, Honolulu, HI, USA, January 2019. (Pdf)

• E. Tugce Ceran, D. Gündüz, and A. György, "A Reinforcement Learning Approach to Age of Information in Multi-User Networks," IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, Bologna, Italy, September 2018. (Pdf)

• S. Somuyiwa, D. Gündüz, and A. György, "Reinforcement Learning for Proactive Caching of Contents with Different Demand Probabilities," 15th International Symposium on Wireless Communication Systems (ISWCS 2018), Lisbon, Portugal, August 2018. (Pdf)

• G. Weisz, A. György, and Cs. Szepesvári, "LeapsAndBounds: A Method for Approximately Optimal Algorithm Configuration," 35th International Conference on Machine Learning (ICML 2018), Stockholm, Sweden, July 2018. (Pdf)

• D. G. Cavezza, D. Alrajeh, and A. György, "A Weakness Measure for GR(1) Formulae," 22nd International Symposium on Formal Methods (FM 2018), Oxford, UK, July 2018. (Pdf)

• S. Somuyiwa, A. György, and D. Gündüz, "A Reinforcement-Learning Approach to Proactive Caching in Wireless Networks," IEEE Journal on Selected Areas of Communications, vol. 36 (3), pp. 1331-1344, June 2018. (Pdf)

• E. Tugce Ceran, D. Gündüz, and A. György, "Average Age of Information with Hybrid ARQ under a Resource Constraint," 2018 IEEE Wireless Communications and Networking Conference (WCNC 2018), Barcelona, Spain, April 2018. (Pdf)

• R. Huang, T. Lattimore, A. György, and Cs. Szepesvári, "Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities," Journal of Machine Learning Research, vol. 18 (145), pp. 1-31, December 2017. (Pdf)

• P. Joulani, A. György, and Cs. Szepesvári, "A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism, Composite Objectives, and Variational Bounds," International Conference on Algorithmic Learning Theory (ALT 2017), Kyoto, Japan, October 2017. (Pdf)

• S. Somuyiwa, A. György, and D. Gündüz, "Energy-Efficient Wireless Content Delivery with Proactive Caching," 2nd Content Caching and Delivery in Wireless Networks Workshop (CCDWN 2017), Paris, France, May 2017. (Pdf)

• S. Somuyiwa, A. György, and D. Gündüz, "Improved Policy RepResentation and Policy Search for Proactive Content Caching in Wireless Networks," 15th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt 2017), Paris, France, May 2017. (Pdf)

• K. Shaloudegi, A. György, Cs. Szepesvári, and W. Xu, "SDP Relaxation with Randomized Rounding for Energy Disaggregation," Advances in Neural Information Processing Systems (NIPS 2016), Barcelona, Spain, December 2016. (Pdf)

• R. Huang, T. Lattimore, A. György, and Cs. Szepesvári, "Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities," Advances in Neural Information Processing Systems (NIPS 2016), Barcelona, Spain, December 2016. (Pdf)

• A. György and Cs. Szepesvári, "Shifting Regret, Mirror Descent, and Matrices," 33rd International Conference on Machine Learning (ICML 2016), New York, USA, July 2016. (Pdf)

• X. Hu, Prashanth L.A., A. György, and Cs. Szepesvári, "(Bandit) Convex Optimization with Biased Noisy Gradient Oracles," 19th International Conference on Artificial Intelligence and Statistics (AISTATS 2016), Cadiz, Spain, May 2016. (Pdf)

• P. Joulani, A. György, and Cs. Szepesvári, "Delay-Tolerant Online Convex Optimization: Unified Analysis and Adaptive-Gradient Algorithms," The Thirtieth AAAI Conference on Artificial Intelligence (AAAI 2016), Phoenix, Arizona, USA, February 2016. (Pdf)

• Y. Wu, A. György, and Cs. Szepesvári, "Online Learning with Gaussian Payoffs and Side Observations," Advances in Neural Information Processing Systems (NIPS 2015), Montreal QC, Canada, December 2015. (Pdf)

• F. Mirzazadeh, M. White, A. György, and D. Schuurmans, "Scalable Metric Learning for Co-embedding," European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2015), Porto, Portugal, September 2015. (Pdf)

• Y. Wu, A. György, and Cs. Szepesvári, "On Identifying Good Options under Combinatorially Structured Feedback in Finite Noisy Environments," International Conference on Machine Learning (ICML 2015), Lille, France, July 2015. (Pdf)

• R. Huang, A. György, and Cs. Szepesvári, "Deterministic Independent Component Analysis," International Conference on Machine Learning (ICML 2015), Lille, France, July 2015. (Pdf)

• P. Joulani, A. György, and Cs. Szepesvári, "Fast Cross-Validation for Incremental Learning," 2015 International Joint Conference on Artificial Intelligence (IJCAI 2015), Buenos Aires, Argentina, July 2015. (Pdf)

• G. Balázs, A. György, and Cs. Szepesvári, "Near-Optimal Max-Affine Estimators for Convex Regression," 18th International Conference on Artificial Intelligence and Statistics (AISTATS 2015), JMLR: W&CP 38, pp. 56-64, San Diego, CA, USA, May 2015. (Pdf)

• R. Shariff, A. György, and Cs. Szepesvári, "Exploiting Symmetries to Construct Efficient MCMC Algorithms with an Application to SLAM," 18th International Conference on Artificial Intelligence and Statistics (AISTATS 2015), JMLR: W&CP 38, pp. 866-874, San Diego, CA, USA, May 2015. (Pdf)

• T. Lattimore, A. György, and Cs. Szepesvári, "On Learning the Optimal Waiting Time," International Conference on Algorithmic Learning Theory (ALT 2014), pp. 200-214, Bled, Slovenia, October 2014. (Pdf)

• B. Hullár, S. Laki, and A. György, "Efficient Methods for Early Protocol Identification," IEEE Journal on Selected Areas in Communications, vol. 32, pp. 1907-1918, October 2014. (Pdf)

• J. Neufeld, A. György, D. Schuurmans, and Cs. Szepesvári, "Adaptive Monte-Carlo via Bandit Allocation," International Conference on Machine Learning (ICML 2014), JMLR: W&CP 32, pp. 1944-1952, Beijing, China, June 2014. (Pdf)

• T. Dick, A. György, and Cs. Szepesvári, "Online Learning in Markov Decision Processes with Changing Reward Sequences," International Conference on Machine Learning (ICML 2014), JMLR: W&CP 32, pp. 512-520, Beijing, China, June 2014. (Pdf)

• A. György and G. Neu, "Near-Optimal Rates for Limited-Delay Universal Lossy Source Coding," IEEE Transactions on Information Theory, vol. 60, pp. 2823-2834, May 2014. (Pdf)

• G. Neu, A. György, Cs. Szepesvári, A. Antos, "Online Markov Decision Processes under Bandit Feedback," IEEE Transactions on Automatic Control, vol. 59, pp. 676-691, March 2014. (Pdf)

• N. Zolghadr, G. Bartók, R. Greiner, A. György, and Cs. Szepesvári, "Online Learning with Costly Features and Labels" Advances in Neural Information Processing Systems (NIPS 2013), pp. 1241-1249, Lake Tahoe, NV, USA, December 2013. (Pdf)

• L. Kocsis, A. György, A. N. Bán, "BoostingTree: Parallel Selection of Weak Learners in Boosting, with Application to Ranking," Machine Learning, vol. 9, pp. 293-320, November 2013. ( Pdf)

• T. Dick, A. György, Cs. Szepesvári, "Online Learning in Markov Decision Processes with Changing Reward Sequences, " 1st Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2013), pp. 198-201, Princeton, NJ, USA, October 2013. (Pdf)

• P. Joulani, A. György, and Cs. Szepesvári, "Online Learning under Delayed Feedback," International Conference on Machine Learning (ICML 2013), JMLR: W&CP 28, vol. 3, pp. 1453-1461, Atlanta, GA, USA, June 2013. (Pdf)

• A. Afkanpour, A. György, Cs. Szepesvári, M. Bowling, "A Randomized Mirror Descent Algorithm for Large Scale Multiple Kernel Learning," International Conference on Machine Learning (ICML 2013), JMLR: W&CP 28, vol. 1, pp. 374-382, Atlanta, GA, USA, June 2013. (Pdf)

• J. Veness, M. White, M. Bowling, and A. György, "Partition Tree Weighting," IEEE Data Compression Conference, pp. 321-330, Snowbird, UT, USA, March 2013. (Pdf)

• A. György, T. Linder, G. Lugosi, "Efficient Tracking of Large Classes of Experts," IEEE Transactions on Information Theory, vol. 58, pp. 6709-6725, November 2012. (Pdf)

• A. György, T. Linder, G. Lugosi, "Efficient Tracking of Large Classes of Experts," IEEE International Symposium on Information Theory, pp. 885-889, Cambridge, MA, USA, July 2012.

• G. Neu, A. György, and Cs. Szepesvári, "The Adversarial Stochastic Shortest Path Problem with Unknown Transition Probabilities," Proceedings of The Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2012), pp. 805-813, La Palma, Canary Islands, April 21-23, 2012. (Pdf, Supplementary)

• L. Devroye, A. György, G. Lugosi, and F. Udina, "High-Dimensional Random Geometric Graphs and Their Clique Number," Electronic Journal of Probability, vol. 16, pp. 2481-2508, 2011. (Pdf)

• A. György and L. Kocsis, "Efficient Multi-Start Strategies for Local Search Algorithms," Journal of Artificial Intelligence Research, vol. 41, pp. 407-444, 2011. (Pdf)

• A. György and G. Neu, "Near-Optimal Rates for Limited-Delay Universal Lossy Source Coding," 2011 IEEE International Symposium on Information Theory, pp. 2218-2222, Saint Petersburg, Russia, July-August 2011. (Pdf)

• B. Hullár, S. Laki, and A. György, "Early Identification of Peer-To-Peer Traffic," IEEE International Conference on Communications (ICC 2011) Next Generation Networking and Internet Symposium, Kyoto, Japan, June 2011. (Pdf)

• G. Neu, A. György, Cs. Szepesvári, and A. Antos, "Online Markov Decision Processes under Bandit Feedback," Advances in Neural Information Processing Systems (NIPS 2010), pp. 1804-1812, Vancouver, Canada, December 6-9, 2010. (Pdf)

• A. György, G. Lugosi, and Gy. Ottucsák, "On-Line Sequential Bin Packing," Journal of Machine Learning Research, vol. 11, pp. 89-109, 2010. (Pdf)

• G. Neu, A. György, and Cs. Szepesvári, "The Online Loop-free Stochastic Shortest-Path Problem," Proceedings of The 23rd Conference on Learning Theory (COLT 2010), OmniPress, pp. 231-243, Haifa, Israel, June 27-29, 2010. (Pdf)

• L. Kocsis and A. György, "Fraud Detection by Generating Positive Samples for Classification from Unlabeled Data," ICML 2010 Workshop on Machine Learning and Games, Haifa, Israel, June 25, 2010. (Pdf)

• P. Torma, A. György, and Cs. Szepesvári, "A Markov-Chain Monte Carlo Approach to Simultaneous Localization and Mapping," Proceedings of The Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2010), JMLR: W&CP 9, pp. 852-859, Chia Laguna, Sardinia, Italy, May 13-15, 2010. (Pdf)

• L. Kocsis and A. György, "Efficient Multi-Start Strategies for Local Search Algorithms," European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2009), Bled, Slovenia, LNAI 5781, Springer, pp. 705-720, September 2009.

• A. György, G. Lugosi, and Gy. Ottucsák, "On-line Sequential Bin Packing," 21th Annual Conference on Learning Theory (COLT 2008), pp. 447-454, Helsinki, Finnland, July 2008.

• A. György, T. Linder, G. Lugosi, "Tracking the Best Quantizer," IEEE Transactions on Information Theory, vol. 54, pp. 1604-1625, April 2008. (Pdf)

• A. György, T. Linder, G. Lugosi, and Gy. Ottucsák, "The On-Line Shortest Path Problem Under Partial Monitoring,"Journal of Machine Learning Research, vol. 8, pp. 2369-2403, October 2007. (Pdf)

• I. Csiszár and A. György, "Multiple Access Channels," in Multiple Access Channels - Theory and Practice, eds. L. Györfi and E. Biglieri, NATO Security through Science Series, D: Information and Communication Security, IOS Press, 2007. pp. 3-17.

• A. György, L. Kocsis, Szabó, Cs. Szepesvári, "Continuous Time Associative Bandit Problems," 2007 International Joint Conference on Artificial Intelligence (IJCAI 2007) pp. 830-835, Hyderabad, India, January 2007. (Pdf with corrections)

• D. A. Nagy, A. György, and T. Linder, "Symbol-Based Modeling and Coding of Block-Markov Sources," IEEE Transactions on Information Theory, vol. 52, pp. 5570-5578, December 2006. (Pdf)

• A. György, T. Linder, and Gy. Ottucsák, "The Shortest Path Problem Under Partial Monitoring," 19th Annual Conference on Learning Theory (COLT 2006), Pittsburgh, PA, USA, LNAI/LNCS 4005, pp. 468-482, June 2006.

• A. György and Gy. Ottucsák, "Adaptive Routing Using Expert Advice," The Computer Journal, vol. 49, pp. 180-189, March 2006. (Pdf)

• A. György, T. Linder, and G. Lugosi, "The Shortest Path Problem in the Bandit Setting," Proceedings of the 2006 IEEE Information Theory Workshop, pp. 87-91, Punta del Este, Uruguay, March 2006.

• A. György, T. Linder, and G. Lugosi, "Limited-Delay Coding of Individual Sequences with Piecewise Different Behavior," 44th IEEE Conference on Decision and Control and European Control Conference, pp. 8185-8190, Sevilla, Spain, December 2005. (invited)

• A. Antos, L. Györfi, and A. György, "Individual Convergence Rates in Empirical Vector Quantizer Design," IEEE Transactions on Information Theory, vol. 51, pp. 4013-4022, November 2005. (Pdf)

• A. György, T. Linder, and G. Lugosi, "Tracking the Best Quantizer," 2005 IEEE International Symposium on Information Theory, pp. 1163-1167, Adelaide, Australia, September 2005.

• A. György, T. Linder, and G. Lugosi, "Tracking the Best of Many Experts," 18th Annual Conference on Learning Theory (COLT 2005), pp. 204-216, Bertinoro, Italy, June 2005.

• A. György, D. A. Nagy, and T. Linder, "Convergence Rates in Higher Order Markov Modeling of Block-Markov Sources," Canadian Workshop on Information Theory, pp. 111-114, Montreal, Quebeck, Canada, June 2005.

• A. György, T. Linder, and G. Lugosi, "Efficient Adaptive Algorithms and Minimax Bounds for Zero-Delay Lossy Source Coding," IEEE Transactions on Signal Processing, vol. 52, pp. 2337-2347, August 2004. (Pdf)

• A. Farkas, A. György, and P. Rózsa, "On the Spectrum of Pairwise Comparison Matrices," Linear Algebra and Its Applications, vol. 385, pp. 443-462, July 2004. (Pdf)

• A. György, T. Linder, and G. Lugosi, "Efficient Algorithms and Minimax Bounds for Zero-Delay Lossy Source Coding," 2004 IEEE International Symposium on Information Theory, p. 461, Chicago, IL, USA, June-July 2004.

• A. Antos, L. Györfi, and A. György, "Improved Convergence Rates in Empirical Vector Quantizer Design," 2004 IEEE International Symposium on Information Theory, p. 300, Chicago, IL, USA, June-July 2004.

• A. György, T. Linder, and G. Lugosi, "A "Follow the Perturbed Leader"-type Algorithm for Zero-Delay Quantization of Individual Sequences," Data Compression Conference, pp. 342-351, Snowbird, UT, USA, March 2004. (Pdf)

• A. György, T. Linder, P. A. Chou, and B. J. Betts, "Do Optimal Entropy-Constrained Quantizers Have a Finite or Infinite Number of Codewords?," IEEE Transactions on Information Theory, vol. IT-49, pp. 3031-3037, November 2003. (Pdf)

• A. György and T. Linder, "Codecell Convexity in Optimal Entropy-Constrained Vector Quantization," IEEE Transactions on Information Theory, vol. IT-49, pp. 1821-1828, July 2003. (Pdf)

• A. György and T. Linder, "Codecell Convexity in Optimal Entropy-Constrained Vector Quantization," 2003 IEEE International Symposium on Information Theory, p. 460, Yokohama, Japan, June-July 2003.

• A. György and T. Linder, "A Note on the Existence of Optimal Entropy-Constrained Vector Quantizers," 2002 IEEE International Symposium on Information Theory, p. 37, Lausanne, Switzerland, June-July 2002.

• A. György and T. Linder, "On the Structure of Optimal Entropy-Constrained Scalar Quantizers," IEEE Transactions on Information Theory, vol. IT-48, pp. 416-427, February 2002. (Pdf)

• A. György and T. Borsos, "Estimates on the Packet Loss Ratio via Queue Tail Probabilities," IEEE GlobeCom 2001, pp. 2407-2411, San Antonio, TX, USA, November 2001. (Pdf)

• A. György and T. Linder, "On the Structure of Entropy-Constrained Scalar Quantizers," 2001 IEEE International Symposium on Information Theory, p. 29, Washington, D.C., USA, June 2001.

• T. Borsos, L. Györfi, and A. György, "On the Second Order Characterization in Traffic Modeling," 9th IFIP Working Conference on Performance Modeling and Evaluation of ATM and IP Networks, pp. 41-49, Budapest, Hungary, June 2001. (Pdf)

• A. György and T. Borsos, "Admission Control for Variable Bit Rate Video Traffic," High Speed Networking 2001 Spring Workshop, pp. 63-69, Balatonfüured, Hungary, May 2001.

• A. György and T. Linder, "Optimal Entropy-Constrained Scalar Quantization of a Uniform Source," IEEE Transactions on Information Theory, vol. IT-46, pp. 2704-2711, November 2000. (Pdf)

• A. György and T. Linder, "Optimal Entropy-Constrained Scalar Quantization of a Uniform Source," 2000 International Symposium on Information Theory and Its Applications, pp. 85-88, Honolulu, HI, USA, November 2000.

• A. György, T. Linder, and K. Zeger, "On the Rate-Distortion Function of Random Vectors and Stationary Sources with Mixed Distributions," IEEE Transactions on Information Theory, vol. IT-45, pp. 2110-2115, September 1999. (Pdf)

• A. György, T. Linder, and K. Zeger, "On the Rate-Distortion Function of Random Vectors and Stationary Sources with Mixed Distributions," 6th Canadian Workshop on Information Theory, pp. 52-55, Kingston, Ont, Canada, June 1999.

• A. György, T. Linder, and K. Zeger, "Lossy Coding of Sources with Mixed Distribution," 33rd Conference on Information Sciences and Systems, pp. 619-623, Baltimore, MD, USA, March 1999.

Theses:

• A. György, "Entropy-Constrained Quantization and Related Problems," Ph.D. Thesis, Department of Computer Science and Information Theory, Budapest University of Technology and Economics, Budapest, Hungary, January 2003.
• A. György, "On Optimal Entropy-Constrained Quantization," M.Sc. Thesis, Department of Mathematics and Statistics, Queen's University, Kingston, Canada, December 2001.
• A. György, "An Analysis of Measurement Based Call Admissin Control Algorithms," M.Sc. Thesis, Department of Computer Science and Information Theory, Technical University of Budapest, Budapest, Hungary, June 1999.