[1] Christos Dimitrakakis, Yang Liu, David Parkes, and Goran Radanovic. Bayesian fairness. In AAAI 2019, 2019. [ bib ]
Keywords: fairness, Bayesian inference, decision theory
[2] Divya Grover and Christos Dimitrakakis. Deeper & sparser sampling. In ICML 2018 workshop on Exploration in Reinforcement Learning, 2018. [ bib | http ]
Keywords: reinforcement learning, Bayesian inference, planning
[3] Aristide C. Y. Tossou and Christos Dimitrakakis. On the differential privacy of thompson sampling with gaussian prior. In ICML 2018 workshop on Privacy in Machine Learning and Artificial Intelligence, 2018. [ bib ]
Keywords: differential privacy
[4] Nikolaos Tziortziotis, Christos Dimitrakakis, and Michalis Vazirgiannis. Randomised bayesian least squares policy iteration. In EWRL, 2018. [ bib ]
Keywords: reinforcement learning, Bayesian inference
[5] Lars Kunze, Mohan Sridharan, Christos Dimitrakakis, and Jeremy Wyatt. Adaptive sampling-based view planning under time constraints. In IEEE European Conference on Mobile Robotics, (ECMR-2017), September 2017. [ bib ]
[6] Brammert Ottens, Christos Dimitrakakis, and Boi Faltings. DUCT: An upper confidence bound approach to distributed constraint optimization problems. ACM Transactions on Intelligent Systems Technology., 8, August 2017. A preliminary version appeared in AAAI 2012. [ bib | http ]
Keywords: distributed constrained optimisation, confidence bounds, complexity, planning
[7] Lars Kunze, Mohan Sridharan, Christos Dimitrakakis, and Jeremy Wyatt. View planning with time constraints: An adaptive sampling approach. In Workshop on AI planning and robotics, ICRA-2017, May 2017. [ bib | .pdf ]
[8] Christos Dimitrakakis, David Parkes, Goran Radanovic, and Paul Tylkin. Multi-view decision processes: The helper-ai problem. In The 31st Annual Conference on Neural Information Processing Systems, (NIPS 2017), 2017. [ bib ]
Keywords: human-AI collaboration, decision theory
[9] Carlo Brunetta, Bei Liang, Christos Dimitrakakis, and Aikaterini Mitrokotsa. A differentially private encryption scheme. In 20th Information Security Conference (ISC 2017), 2017. [ bib ]
Keywords: security, differential privacy
[10] Philip Ekman, Sebastian Bellevik, Christos Dimitrakakis, and Aristide C. Y. Tossou. Learning to match. In Value-Aware and Multi-Stakeholder Recommendation, at RecSys-2017, 2017. [ bib ]
Keywords: recommendation systems
[11] Nikolaos Tziortziotis and Christos Dimitrakakis. Bayesian inference for least squares temporal difference regularization. In ECML, 2017. [ bib ]
Keywords: reinforcement learning, Bayesian inference
[12] Christos Dimitrakakis, Blaine Nelson, Zuhe Zhang, Aikaterini Mitrokotsa, and Benjamin I. P. Rubinstein. Differential privacy for Bayesian inference through posterior sampling. Journal of Machine Learning Research, 18(11):1--39, 2017. [ bib | .html ]
Keywords: differential privacy, Bayesian inference
[13] Aristide C. Y. Tossou and Christos Dimitrakakis. Achieving privacy in the adversarial multi-armed bandit. In 14th International Conference on Artificial Intelligence (AAAI 2017), 2017. [ bib | http ]
Keywords: differential privacy, bandits, regret, reinforcement learning, privacy, machine learning
[14] Aristide C. Y. Tossou, Christos Dimitrakakis, and Devdatt Dubhashi. Thompson sampling for stochastic bandits with graph feedback. In 14th International Conference on Artificial Intelligence (AAAI 2017), 2017. [ bib | http ]
Keywords: bandits, regret, reinforcement learning, graphs, partial information, prediction, online learning
[15] Christos Dimitrakakis, Yang Liu, David Parkes, and Goran Radanovic. Bayesian fairness. Technical Report 1706.00119, arXiv, 2017. [ bib | http ]
Keywords: fairness, Bayesian inference, decision theory
[16] Christos Dimitrakakis, Yang Liu, , Debmalya Mandal, David Parkes, and Goran Radanovic. Calibrated fairness in bandits. In Fairness, Accountability and Transparency in Machine Learning, (FAT-ML-17) at KDD, 2017. [ bib ]
Keywords: fairness, multi-armed bandits
[17] Christos Dimitrakakis, Yang Liu, , Debmalya Mandal, David Parkes, and Goran Radanovic. Fair experimentation. In Conference on Digital Experimentation (CODE-17), 2017. [ bib ]
Keywords: fairness, multi-armed bandits
[18] Aristide C. Y. Tossou and Christos Dimitrakakis. Algorithms for differentially private multi-armed bandits. In 13th International Conference on Artificial Intelligence (AAAI 2016), 2016. [ bib ]
Keywords: differential privacy, bandits, regret, reinforcement learning, privacy, machine learning
[19] Zuhe Zhang, Benjamin I. P. Rubinstein, and Christos Dimitrakakis. On the differential privacy of Bayesian inference. In 13th International Conference on Artificial Intelligence (AAAI 2016), 2016. [ bib ]
Keywords: differential privacy, Bayesian inference, discrete Bayesian networks, linear regression, privacy, machine learning
[20] Christos Dimitrakakis, Firas Jarboui, David Parkes, and Lior Seeman. Multi-view sequential games: The helper-agent problem. Technical Report hal-01408294, 2016. [ bib | http ]
Keywords: decision theory, helper-ai
[21] Christos Dimitrakakis and Aikaterini Mitrokotsa. Near-optimal blacklisting. Computers & Security, July 2015. [ bib ]
Keywords: algorithmic analysis, security, distance bounding, authentication, POMDP, MDP, reinforcement learning, machine learning
[22] Christos Dimitrakakis and Aikaterini Mitrokotsa. Distance-bounding protocols: Are you close enough? IEEE Security & Privacy, 13(4):47--51, July--August 2015. [ bib ]
Keywords: distance bounding, authentication, security
[23] Aristide C. Y. Tossou and Christos Dimitrakakis. Differentially private, multi-agent multi-armed bandits. In European Workshop on Reinforcement Leanring (EWRL), 2015. [ bib ]
Keywords: bandits, differential privacy, privacy, multi-agent, reinforcement learning, machine learning
[24] Christos Dimitrakakis, Aikaterini Mitrokotsa, and Serge Vaudenay. Expected loss bounds for authentication in constrained channels. Journal of Computer Security, 23(3):309--329, 2015. [ bib | DOI ]
Keywords: algorithmic analysis, security, distance bounding, authentication
[25] Elena Pagnin, Christos Dimitrakakis, Aysajan Abidin, and Aikaterini Mitrokotsa. On the leakage of information in biometric authentication. In Indocrypt 2014, 2014. [ bib ]
Keywords: authentication, security
[26] Christos Dimitrakakis, Guangliang Li, and Nikolaos Tziortziotis. The reinforcement learning competition 2014. AI Magazine, 35(3):61--65, 2014. [ bib ]
Keywords: reinforcement learning, competition
[27] Emmanouil Androulakis and Christos Dimitrakakis. Generalised entropy MDPs and minimax regret. In NIPS 2014 Workshop: From bad models to good policies, 2014. [ bib ]
Keywords: zero-sum games, game theory, MDP, bandits, experts, complexity, reinforcement learning, machine learning
[28] Christos Dimitrakakis and Nikolaos Tziortziotis. Usable ABC reinforcement learning. In NIPS 2014 Workshop: ABC in Montreal, 2014. [ bib ]
Keywords: Approximate Bayesian Computation, Bayesian inference, reinforcement learning, approximately sufficient statistics, simulation, Monte-Carlo tree search, machine learning
[29] Christos Dimitrakakis, Blaine Nelson, Aikaterini Mitrokotsa, and Benjamin I. P. Rubinstein. Robust and private Bayesian inference. In Algorithmic Learning Theory, 2014. [ bib ]
Keywords: bayesian inference, robust statistics, security, privacy, differential privacy, distinguishability, estimation, prior distributions, machine learning
[30] Nikolaos Tziortziotis, Christos Dimitrakakis, and Konstantinos Blekas. Cover tree Bayesian reinforcement learning. Journal of Machine Learning Research (JMLR), 2014. [ bib ]
Keywords: cover trees, non-parametric Bayesian models, Bayesian inference, approximate dynamic programming, Thompson sampling
[31] Florent Gardin, Christos Dimitrakakis, and Boi Faltings. Personalized news recommendation using context trees. In ACM Conference on Recommender Systems (RecSys 2013), 2013. [ bib ]
Keywords: recommendation systems, context trees
[32] Christos Dimitrakakis. Monte-carlo utility estimates for bayesian reinforcement learning. In IEEE 52nd Annual Conference on Decision and Control (CDC 2013), 2013. arXiv:1303.2506. [ bib ]
Keywords: reinforcement learning, Bayesian inference, stochastic gradient descent, Monte Carlo, decision theory, Bellman error, machine learning
[33] Aikaterini Mitrokotsa, Pedro Peris-Lopez, Christos Dimitrakakis, and Serge Vaudenay. On selecting the nonce length in distance-bounding protocols. The Computer Journal, 56(10):1216--1227, 2013. [ bib | DOI | arXiv | http ]
Keywords: high probability bounds, cryptanalysis, algorithmic analysis, martingales, security, RFID, distance bounding, relay attacks, authentication
[34] Pengsheng Zhang, Christos Dimitrakakis, and Jochen Triesch. Network self-organization explains the statistics and dynamics of synaptic connection strengths in cortex. PLoS Computational Biology, 9(1):e1002848, 2013. [ bib | DOI ]
Keywords: neuroscience, statistical analysis, synaptic dynamics, neural networks
[35] Bernhard Wymann, Christos Dimitrakakis, Andrew Sumner, Eric Espié, Christophe Guionneau, and Rémi Coulom. TORCS, the open racing car simulator, v1.3.5. http://www.torcs.org, 2013. [ bib ]
Keywords: racing, software, robots, driving, artificial intelligence, simulation
[36] Christos Dimitrakakis, Blaine Nelson, Aikaterini Mitrokotsa, and Benjamin I. P. Rubinstein. Robust, secure and private Bayesian inference. Technical Report abs/1306.1066, arXiv, 2013. [ bib ]
Keywords: bayesian inference, robust statistics, security, privacy, differential privacy, distinguishability, estimation, prior distributions, machine learning
[37] Aristide Tossou and Christos Dimitrakakis. Probabilistic inverse reinforcement learning in unkown environments. In UAI 2013, 2013. To appear. [ bib ]
Keywords: probabilistic inference, inverse reinforcement learning, apprenticeship learning
[38] Nikolaos Tziortziotis, Christos Dimitrakakis, and Konstantinos Blekas. Linear Bayesian reinforcement learning. In Proceedings of the 23rd international joint conference on artififical intelligence (IJCAI 2013), 2013. [ bib ]
Keywords: Bayesian inference, approximate dynamic programming, Thompson sampling, continuous state space
[39] Christos Dimitrakakis and Nikolaos Tziortziotis. ABC reinforcement learning. In ICML 2013, volume 28(3) of JMLR W & CP, pages 684--692, 2013. See also arXiv:1303.6977. [ bib ]
Keywords: bayesian inference, approximate Bayesian computation, approximate dynamic programming, Thompson sampling
[40] Christos Dimitrakakis, Aikaterini Mitrokotsa, and Serge Vaudenay. Expected loss bounds for authentication in constrained channels. In INFOCOM, 2012 Proceedings IEEE, pages 478--485, march 2012. [ bib | DOI ]
Keywords: algorithmic analysis, security, distance bounding, authentication
[41] Luca Lonini, Christos Dimitrakakis, Constantin A. Rothkopf, and Jochen Triesch. Computational and Robotic Models of the Hierarchical Organization of Behavior, chapter Generalization and interference in human motor control. Springer, 2012. [ bib ]
Keywords: reinforcement learning, hierarchical architectures
[42] Christos Dimitrakakis. Sparse reward processes. Technical Report abs/1201.2555, arXiv, 2012. Presented at Dagstuhl Seminar on Machine Learning and Security. [ bib ]
Keywords: Reinforcement learning, multi-task learning, curiosity, security, decision theory, regret, machine learning
[43] Brammert Ottens, Christos Dimitrakakis, and Boi Faltings. DUCT: An upper confidence bound approach to distributed constraint optimization problems. In AAAI 2012, 2012. [ bib ]
Keywords: distributed constrained optimisation, confidence bounds, complexity, planning
[44] Aikaterini Mitrokotsa and Christos Dimitrakakis. Intrusion detection in manet using classification algorithms: The effects of cost and model selection. Ad-Hoc Networks, 2012. [ bib ]
Keywords: classification, security, machine learning
[45] Florent Garcin, Christos Dimitrakakis, and Boi Faltings. Variable order Markov model recommender systems for personalized news recommendation. Technical Report arXiv:1303.0665, 2012. [ bib ]
Keywords: variable order Markov model, recommender system, Bayesian inference
[46] Christos Dimitrakakis. Context models on sequences of covers. Technical Report arXiv:1005.2263, arXiv, 2011. [ bib ]
Keywords: conditional density estimation, Bayesian inference, non-parametric models, machine learning
[47] Pengsheng Zhang, Christos Dimitrakakis, and Jochen Triesch. Network self-organization explains distribution of synaptic efficacies in neocortex. In DeveLeaNN 2011: Workshop on Development and Learning in Artificial Neural Networks, 2011. [ bib ]
Keywords: neuroscience, statistical analysis, synaptic dynamics, neural networks
[48] Christos Dimitrakakis, Aikaterini Mitrokotsa, and Serge Vaudenay. Expected loss analysis of thresholded authentication protocols in noisy conditions. Technical Report 1009.0278, arXiv, 2011. [ bib ]
Keywords: algorithmic analysis, security, distance bounding, authentication
[49] Christos Dimitrakakis and Samy Bengio. Phoneme and sentence-level ensembles for speech recognition. EURASIP Journal on Audio, Speech and Music Processing, 2011. [ bib ]
Keywords: speech recognition, ensemble methods, boosting, bagging, machine learning
[50] Christos Dimitrakakis. Robust bayesian reinforcement learning through tight lower bounds. In European Workshop on Reinforcement Learning (EWRL 2011), number 7188 in LNCS, pages 177--188, 2011. [ bib ]
Keywords: reinforcement learning, Bayesian inference, Thompson sampling, value function bounds, complexity, planning, machine learning
[51] Christos Dimitrakakis and Constantin A. Rothkopf. Bayesian multitask inverse reinforcement learning. In European Workshop on Reinforcement Learning (EWRL 2011), number 7188 in LNCS, pages 273--284, 2011. [ bib ]
Keywords: inverse reinforcement learning, apprenticeship learning, Bayesian inference, multi-task learning, complexity, behavioural modelling, machine learning
[52] Constantin A. Rothkopf and Christos Dimitrakakis. Preference elicitation and inverse reinforcement learning. In ECML/PKDD (3), volume 6913 of LNCS, pages 34--48, 2011. [ bib ]
Keywords: Inverse reinforcement learning, apprenticeship learning, Bayesian inference, behavioural modelling, machine learning
[53] Christos Dimitrakakis. Variable order Markov decision processes: Exact Bayesian inference with an application to POMDPs. Technical report, FIAS, May 2010. http://fias.uni-frankfurt.de/~dimitrakakis/papers/tr-fias-10-05.pdf. [ bib ]
Keywords: POMDP, Bayesian inference, approximate dynamic programming
[54] Pedro Peris-Lopez, Julio C. Hernandez-Castro, Christos Dimitrakakis, Aikaterini Mitrokotsa, and Juan M. E. Tapiador. Shedding light on RFID distance bounding protocols and terrorist fraud attacks. Technical Report 0906.4618, arXiv, 2010. [ bib ]
Keywords: RFID, security, authentication
[55] Christos Dimitrakakis. Efficient methods for near-optimal sequential decision making under uncertainty. In Robert Babuska and Frans Groen, editors, Interactive Collaborative Information Systems, volume 281 of SCI, pages 125--153. Springer, 2010. [ bib ]
Keywords: Bayesian inference, statistics, reinforcement learning, decision theory, planning, machine learning
[56] Aikaterini Mitrokotsa, Christos Dimitrakakis, Pedro Peris-Lopez, and Julio C. Hernandez-Castro. Reid et al.'s distance bounding protocol and mafia fraud attacks over noisy channels. IEEE Communication Letters, 14(2):121--123, 2010. [ bib ]
Keywords: RFID, security, distance bounding, algorithmic analysis
[57] Christos Dimitrakakis. Context model inference for large or partially observable MDPs. In ICML workshop on reinforcement learning and search in very large spaces, 2010. [ bib ]
Keywords: reinforcement learning, Bayesian inference, approximate dynamic programming, machine learning
[58] Christos Dimitrakakis. Bayesian variable order Markov models. In Yee Whye Teh and Mike Titterington, editors, Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS), volume 9 of JMLR : W&CP, pages 161--168, Chia Laguna Resort, Sardinia, Italy, 2010. [ bib ]
Keywords: Bayesian inference, prediction, non-parametric models, machine learning
[59] Christos Dimitrakakis. Complexity of stochastic branch and bound methods for belief tree search in Bayesian reinforcement learning. In 2nd international conference on agents and artificial intelligence (ICAART 2010), pages 259--264, Valencia, Spain, 2010. ISNTICC, Springer. [ bib ]
Keywords: Bayesian inference, reinforcement learning, exploration-exploitation, planning, stochastic branch and bound, Thompson sampling, value function bounds, complexity, bandits
[60] Christos Dimitrakakis. Bayesian variable order Markov models: Towards Bayesian predictive state representations. Technical Report IAS-UVA-09-04, University of Amsterdam, June 2009. [ bib ]
Keywords: POMDP, variable order Markov model, Bayesian inference, approximate dynamic programming, predictive state representations
[61] Christos Dimitrakakis. Complexity of stochastic branch and bound for belief tree search in Bayesian reinforcement learning. Technical Report IAS-UVA-09-01, University of Amsterdam, April 2009. [ bib ]
[62] Christos Dimitrakakis and Aikaterini Mitrokotsa. Statistical decision making for authentication and intrusion detection. In Machine Learning and Applications, Fourth International Conference on (ICMLA'09), pages 409--414, Miami, FL, USA, 2009. IEEE Computer Society. [ bib | DOI ]
Keywords: Bayesian inference, minimax priors, security, authentication, machine learning
[63] Christos Dimitrakakis and Michail G. Lagoudakis. Rollout sampling approximate policy iteration. Machine Learning, 72(3):157--171, September 2008. Presented at ECML'08. [ bib | DOI ]
Keywords: reinforcement learning, policy iteration, rollouts, bandits, upper confidence bounds, machine learning
[64] Christos Dimitrakakis and Christian Savu-Krohn. Cost-minimising strategies for data labelling: optimal stopping and active learning. In Proceedings of the 5th international symposium on Foundations of Information and Knowledge Systems (FoIKS 2008), volume 4932 of Lecture Notes in Computer Science, pages 96--111, Pisa, Italy, February 2008. Springer. [ bib ]
Keywords: active learning, Bayesian inference, optimal stopping, planning, machine learning
[65] Christos Dimitrakakis. Exploration in POMDPs. Österreichische Gesellschaft für Artificial Intelligence Journal, 1:24--31, 2008. [ bib ]
Keywords: reinforcement learning, Bayesian inference, POMDP, exploration-exploitation, decision theory, planning, machine learning
[66] Christos Dimitrakakis. Tree exploration for Bayesian RL exploration. In Computational Intelligence for Modelling, Control and Automation, International Conference on, pages 1029--1034, Wien, Austria, 2008. IEEE Computer Society. [ bib | DOI ]
Keywords: Bayesian inference, reinforcement learning, exploration-exploitation, planning, Thompson sampling, value function bounds, bandits
[67] Christos Dimitrakakis and Michail G. Lagoudakis. Algorithms and bounds for rollout sampling approximate policy iteration. In EWRL, pages 27--40, 2008. [ bib ]
Keywords: Reinforcement learning, rollout algorithms, resource allocation, approximate policy iteration, machine learning
[68] Christos Dimitrakakis, Nikolaos Tziortziotis, and Aristide Tossou. Beliefbox: A framework for statistical methods in sequential decision making. http://code.google.com/p/beliefbox/, 2007. [ bib ]
Keywords: Bayesian inference, statistics, reinforcement learning, algorithms, machine learning
[69] Aikaterini Mitrokotsa, Christos Dimitrakakis, and Christos Douligeris. Intrusion detection using cost-sensitive classification. In Proceedings of the 3rd European Conference on Computer Network Defense (EC2ND'07), volume 30 of LNEE (Lecture Notes in Electrical Engineering), pages 35--46, Heraklion, Greece, 4-5 October 2007. Springer. [ bib ]
Keywords: classification, intrusion detection, security, machine learning
[70] Christos Dimitrakakis. Nearly optimal exploration-exploitation decision thresholds. In Int. Conf. on Artificial Neural Networks (ICANN), 2006. [ bib ]
Keywords: bootstrapping, reinforcement learning, exploration-exploitation, Thompson sampling, confidence bounds, ensemble methods, machine learning
[71] Christos Dimitrakakis. Online statistical estimation for vehicle control. IDIAP-RR 13, IDIAP, 2006. [ bib ]
[72] Christos Dimitrakakis. Ensembles for Sequence Learning. PhD thesis, École Polytechnique Fédérale de Lausanne, 2006. [ bib ]
Keywords: ensemble methods, bootstrapping, boosting, bagging, mixture of experts, speech recognition, reinforcement learning, exploration-exploitation, uncertainty, sequence learning, sequential decision making, Thompson sampling, machine learning
[73] Christos Dimitrakakis and Samy Bengio. Online policy adaptation for ensemble classifiers. Neurocomputing, 64:211--221, 2005. [ bib ]
Keywords: reinforcement learning, ensemble methods, classification, machine learning
[74] Christos Dimitrakakis and Samy Bengio. Gradient-based estimates of return distributions. In PASCAL workshop on principled methods of trading exploration and exploitation. PASCAL Network, 2005. [ bib ]
Keywords: reinforcement learning, gradient descent, exploration-exploitation, machine learning
[75] Christos Dimitrakakis and Samy Bengio. Boosting word error rates. In Proceedings of the IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP), volume 5, pages 501--504, 2005. [ bib ]
Keywords: speech recognition, ensemble methods, hidden Markov models
[76] Christos Dimitrakakis and Samy Bengio. Gradient estimates of return. IDIAP-RR 05-29, IDIAP, 2005. [ bib ]
Keywords: reinforcement learning, distributional reinforcement learning
[77] Christos Dimitrakakis and Samy Bengio. Boosting HMMs with an application to speech recognition. In Proceedings of the IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP), volume 5, pages 621--624, 2004. [ bib ]
Keywords: speech recognition, ensemble methods, hidden Markov models
[78] Christos Dimitrakakis and Samy Bengio. Online Policy Adaptation for Ensemble Classifiers. In 12th European Symposium on Artificial Neural Networks, ESANN, volume 4, 2004. [ bib ]
Keywords: reinforcement learning, ensemble methods, classification
[79] Christos Dimitrakakis and Samy Bengio. Estimates of parameter distributions for optimal action selection. Technical Report 04-72, IDIAP, 2004. [ bib ]
Keywords: reinforcement learning, exploration-exploitation, uncertainty
[80] Christos Dimitrakakis. Reinforcement learning with continuous action values, 1999. http://christos.dimitrakakis.googlepages.com/RLContAction.ps.gz. [ bib ]
Keywords: reinforcement learning

This file was generated by bibtex2html 1.98.