Travelled to:1 × Canada
1 × China
1 × France
1 × Israel
1 × USA
1 × United Kingdom
Collaborated with:B.Kégl B.Szörényi E.Hüllermeier P.Weng D.Benbouzid W.Cheng I.Hegedüs R.Ormándi M.Jelasity
Talks about:base (5) bandit (3) use (3) prefer (2) boost (2) fast (2) distribut (1) algorithm (1) adversari (1) stochast (1)
Person: Róbert Busa-Fekete
DBLP: Busa-Fekete:R=oacute=bert
Contributed to:
201520142013201220102009Wrote 7 papers:
- ICML-2015-SzorenyiBWH #approach #multi
- Qualitative Multi-Armed Bandits: A Quantile-Based Approach (BS, RBF, PW, EH), pp. 1660–1668.
- ICML-c2-2014-Busa-FeketeHS #elicitation #modelling #rank #statistics #using
- Preference-Based Rank Elicitation using Statistical Models: The Case of Mallows (RBF, EH, BS), pp. 1071–1079.
- ICML-c3-2013-Busa-FeketeSCWH #adaptation
- Top-k Selection based on Adaptive Sampling of Noisy Preferences (RBF, BS, WC, PW, EH), pp. 1094–1102.
- ICML-c3-2013-SzorenyiBHOJK #algorithm #distributed #probability
- Gossip-based distributed stochastic bandit algorithms (BS, RBF, IH, RO, MJ, BK), pp. 19–27.
- ICML-2012-Busa-FeketeBK #classification #graph #performance #using
- Fast classification using sparse decision DAGs (RBF, DB, BK), p. 99.
- ICML-2010-Busa-FeketeK #performance #using
- Fast boosting using adversarial bandits (RBF, BK), pp. 143–150.
- ICML-2009-KeglB #classification
- Boosting products of base classifiers (BK, RBF), pp. 497–504.