Christos Dimitrakakis

Professor - PROG Programmering

English version of this page

E-post chridim@ifi.uio.no

Brukernavn

Besøksadresse Gaustadalléen 23B 0373 Oslo

Postadresse Postboks 1080 0316 Oslo

Last ned visittkort

Jeg er forsker innen Maskinlæring og mine viktigste interesser er:

Undervisning

Jeg underviser IN-STK5000, Adaptive methods for data-based decision making, med emner:

Emneord: maskinlæring, reinforcement learning, differential privacy, Kunstig intelligens, personvern

Publikasjoner

Bayesian fairness, AAAI 2019.
Randomised Bayesian Least-Squares Policy Iteration, EWRL 2018.
Multi-View Decision Processes, [poster] [video] [slides] NIPS 2017.
Calibrated fairness In bandits, FATML-17.
Differential privacy for Bayesian Inference through posterior sampling, JMLR, 2017.
Achieving privacy in the adversarial multi-armed bandit, AAAI 2017.
Cover tree Bayesian reinforcement learning. J. Mach. Learn. Res. 15(1): 2313-2335 (2014)
ABC Reinforcement Learning. ICML (3) 2013: 684-692
Probabilistic inverse reinforcement learning in unknown environments. UAI 2013
Robust Bayesian Reinforcement Learning through Tight Lower Bounds. EWRL 2011: 177-188
Bayesian Multitask Inverse Reinforcement Learning. EWRL 2011: 273-284
Complexity of stochastic branch and bound methods for belief tree search in Bayesian reinforcement learning. CoRR abs/0912.5029 (2009)
Rollout sampling approximate policy iteration. Machine Learning 72(3): 157-171 (2008)
Nearly Optimal Exploration-Exploitation Decision Thresholds. ICANN (1) 2006: 850-859

Dimitrakakis, Christos; Liu, Yang; Parkes, David C. & Radanovic, Goran (2019). Bayesian fairness, Proceedings of the AAAI Conference on Artificial Intelligence. AAAI Press. ISSN 978-1-57735-809-1. doi: https%3A/doi.org/10.1609/aaai.v33i01.3301509.
Ekström, Andreas; Forssen, Christian; Dimitrakakis, Christos; Dubhashi, Devdatt; Johansson, H. T. & Salomonsson, Hans [Vis alle 7 forfattere av denne artikkelen] (2019). Bayesian optimization in ab initio nuclear physics . Journal of Physics G: Nuclear and Particle Physics. ISSN 0954-3899. 46(9). doi: 10.1088/1361-6471/ab2b14.
Dimitrakakis, Christos; Nelson, Blaine; Zhang, Zuhe; Mitrokotsa, Aikateirni & Rubinstein, Benjamin I.P. (2017). Differential privacy for Bayesian inference through posterior sampling. Journal of machine learning research. ISSN 1532-4435. 18(1).

Kleine Büning, Thomas; George, Anne-Marie & Dimitrakakis, Christos (2021). Interactive Inverse Reinforcement Learning for Cooperative Games.
Dimitrakakis, Christos (2020). Differential privacy in energy systems.
Jorge, Emilio; Eriksson, Hannes; Dimitrakakis, Christos; Basu, Debabrota & Grover, Divya (2020). Inferential Induction: A Novel Framework for Bayesian Reinforcement Learning.
Eriksson, Hannes & Dimitrakakis, Christos (2020). Epistemic Risk-Sensitive Reinforcement Learning .
Grover, Divya; Basu, Debabrota & Dimitrakakis, Christos (2020). Bayesian Reinforcement Learning via Deep, Sparse Sampling.
Tossou, Aristide; Dimitrakakis, Christos; Rzepecki, Jaroslaw & Hofmann, Katja (2020). A Novel Individually Rational Objective In Multi-Agent Multi-Armed Bandits: Algorithms and Regret Bounds.
Boroujeni, Mahrokh Ghoddousi; Fay, Dominik; Dimitrakakis, Christos & Kamgarpour, Maryam (2019). Privacy of Real-Time Pricing in Smart Grid.
Dimitrakakis, Christos; Liu, Yang; Parkes, David C. & Radanovic, Goran (2019). Bayesian fairness.
Dimitrakakis, Christos; Parkes, David C.; Radanovic, Goran & Tylkin, Paul (2017). Multi-View Decision Processes: The Helper-AI Problem.

Publisert 16. okt. 2019 09:40