Gergely Neu

gneu's picture

Gergely Neu is a postdoctoral researcher funded by the UPFellows grant since 2015. He obtained his PhD degree in Computer Science from the Budapest University of Technology and Economics (Hungary) in 2013  and have consecutively spent two years as a postdoctoral researcher at the SequeL team of INRIA Lille (France) between 2013 and 2015. He is mainly interested in theoretical aspects of machine learning for sequential decision making, especially the interplay between computational and statistical efficiency of online learning algorithms.

Publications

T. Kocák, Neu, G., and Valko, M., Online learning with noisy side observations, in International Conference on Artificial Intelligence and Statistics, 2016, pp. 1186–1194.
T. Kocák, Neu, G., and Valko, M., Online learning with Erdős-Rényi side-observation graphs, in Uncertainty in Artificial Intelligence, 2016, pp. 339–347.
L. Devroye, Lugosi, G., and Neu, G., Random-walk perturbations for online combinatorial optimization, IEEE Transactions on Information Theory, vol. 61, pp. 4099-4106, 2015.
G. Neu, First-order regret bounds for combinatorial semi-bandits, in {Proceedings of the 27th Annual Conference on Learning Theory (COLT)}, 2015, pp. 1360-1375.
T. \vs Kocák, Neu, G., Valko, M., and Munos, R., Efficient learning by implicit exploration in bandit problems with side observations, in Advances in Neural Information Processing Systems 27 (NIPS), 2014, pp. 613-621.
G. Neu and Valko, M., Online combinatorial optimization with stochastic decision sets and adversarial losses, in Advances in Neural Information Processing Systems 27 (NIPS), 2014, pp. 2780-2788.
A. Sani, Neu, G., and Lazaric, A., Exploiting easy data in online optimization, in Advances in Neural Information Processing Systems 27 (NIPS), 2014, pp. 810-818.
A. György and Neu, G., Near-Optimal Rates for Limited-Delay Universal Lossy Source Coding, IEEE Transactions on Information Theory, vol. 60, pp. 2823–2834, 2014.

Pages